Is AGI just a question of scale now – AGI part-5

Read two articles over the past month or so. The more recent one was an Economist article (AI enters the industrial age, paywall) and the other was A generalist agent (from Deepmind). The Deepmind article was all about the training of Gato, a new transformer deep learning model trained to perform well on 600 separate task arenas from image captioning, to Atari games, to robotic pick and place tasks.

And then there was this one tweet from Nando De Frietas, research director at Deepmind:

Someone’s opinion article. My opinion: It’s all about scale now! The Game is Over! It’s about making these models bigger, safer, compute efficient, faster at sampling, smarter memory, more modalities, INNOVATIVE DATA, on/offline, … 1/N

I take this to mean that AGI is just a matter of more scale. Deepmind and others see the way to attain AGI is just a matter of throwing more servers, GPUs and data at the training the model.

We have discussed AGI in the past (see part-0 [ish], part-1 [ish], part-2 [ish], part-3ish and part-4 blog posts [We apologize, only started numbering them at 3ish]). But this tweet is possibly the first time we have someone in the know, saying they see a way to attain AGI.

Transformer models

It’s instructive from my perspective that, Gato is a deep learning transformer model. Also the other big NLP models have all been transformer models as well.

Gato (from Deepmind), SWITCH Transformer (from Google), GPT-3/GPT-J (from OpenAI), OPT (from meta), and Wu Dai 2.0 (from China’s latest supercomputer) are all trained on more and more text and image data scraped from the web, wikipedia and other databases.

Wikipedia says transformer models are an outgrowth of RNN and LSTM models that use attention vectors on text. Attention vectors encode, into a vector (matrix), all textual symbols (words) prior to the latest textual symbol. Each new symbol encountered creates another vector with all prior symbols plus the latest word. These vectors would then be used to train RNN models using all vectors to generate output.

The problem with RNN and LSTM models is that it’s impossible to parallelize. You always need to wait until you have encountered all symbols in a text component (sentence, paragraph, document) before you can begin to train.

Instead of encoding this attention vectors as it encounters each symbol, transformer models encode all symbols at the same time, in parallel and then feed these vectors into a DNN to assign attention weights to each symbol vector. This allows for complete parallelism which also reduced the computational load and the elapsed time to train transformer models.

And transformer models allowed for a large increase in DNN parameters (I read these as DNN nodes per layer X number of layers in a model). GATO has 1.2B parameters, GPT-3 has 175B parameters, and SWITCH Transformer is reported to have 7X more parameters than GPT-3 .

Estimates for how much it cost to train GPT-3 range anywhere from $10M-20M USD.

AGI will be here in 10 to 20 yrs at this rate

So if it takes ~$15M to train a 175B transformer model and Google has already done SWITCH which has 7-10X (~1.5T) the number of GPT-3 parameters. It seems to be an arms race.

If we assume it costs ~$65M (~2X efficiency gain since GPT-3 training) to train SWITCH, we can create some bounds as to how much it will cost to train an AGI model.

By the way, the number of synapses in the human brain is approximately 1000T (See Basic NN of the brain, …). If we assume that DNN nodes are equivalent to human synapses (a BIG IF), we probably need to get to over 1000T parameter model before we reach true AGI.

So my guess is that any AGI model lies somewhere between 650X to 6,500X parameters beyond SWITCH or between 1.5Q to 15Q model parameters.

If we assume current technology to do the training this would cost $40B to $400B to train. Of course, GPUs are not standing still and NVIDIA’s Hopper (introduced in 2022) is at least 2.5X faster than their previous gen, A100 GPU (introduced in 2020). So if we waited a 10 years, or so we might be able to reduce this cost by a factor of 100X and in 20 years, maybe by 10,000X, or back to where roughly where SWITCH is today.

So in the next 20 years most large tech firms should be able to create their own AGI models. In the next 10 years most governments should be able to train their own AGI models. And as of today, a select few world powers could train one, if they wanted to.

Where they get the additional data to train these models (I assume that data counts would go up linearly with parameter counts) may be another concern. However, I’m sure if you’re willing to spend $40B on AGI model training, spending a few $B more on data acquisition shouldn’t be a problem.

~~~~

At the end of the Deepmind article on Gato, it talks about the need for AGI safety in terms of developing preference learning, uncertainty modeling and value alignment. The footnote for this idea is the book, Human Compatible (AI) by S. Russell.

Preference learning is a mechanism for AGI to learn the “true” preference of a task it’s been given. For instance, if given the task to create toothpicks, it should realize the true preference is to not destroy the world in the process of making toothpicks.

Uncertainty modeling seems to be about having AI assume it doesn’t really understand what the task at hand truly is. This way there’s some sort of (AGI) humility when it comes to any task. Such that the AGI model would be willing to be turned off, if it’s doing something wrong. And that decision is made by humans.

Deepmind has an earlier paper on value alignment. But I see this as the ability of AGI to model human universal values (if such a thing exists) such as the sanctity of human life, the need for the sustainability of the planet’s ecosystem, all humans are created equal, all humans have the right to life, liberty and the pursuit of happiness, etc.

I can see a future post is needed soon on Human Compatible (AI).

Photo Credit(s):

Better autonomous drone flying with Neural-Fly

Read an article the other day on Neural-Fly (see: Rapid adaptation of deep learning teaches drones to survive any weather) based on research out of CalTech documented in a paper is ScienceRobotics (see: Neural-Fly enables rapid learning for agile flight in strong winds, behind paywall).

Essentially they have trained two neural networks (NN) at the same time and computed an adaptation coefficient matrix (with linear multipliers to compensate for wind speed). The first NN is trained to understand the wind invariant flight characteristics of a drone in wind and the second is trained to the predict the class of wind the drone is flying in (or wind index). These two plus the adaptation control matrix coefficients are used to predict the resultant force on drone flight in wind.

In a CalTech article on the research (see: Rapid Adaptation of Deep Learning Teaches Drones to Survive Any Weather) at the bottom is a YouTube video that shows how well the drone can fly in various wind conditions (up to 27mph).

The data to train the two NNs and compute the adaptation matrix coefficients come from CalTech wind tunnel results with their custom built drone (essentially an RPi4 added to a pretty standard drone) doing random trajectories under different static wind conditions.

The two NNs and the adaptation control matrix functionality run on a Raspberry Pi 4 (RPi4) that’s added to a drone they custom built for the test vehicle. The 2 NNs and the adaptation control tracking are used in the P-I-D (proportional-integral-derivative) controller for drone path prediction. The Neural-Fly 2 NNs plus the adaptation functionality effectively replaces the residual force prediction portion of Integral section of the P-I-D controller.

The wind invariant neural net has 5 layers with relatively few parameters per layer. The wind class prediction neural network has 3 layers and even fewer parameters. Together these two NNs plus the adaptation coefficient provides real time resultant force predictions on the drone which can be fed into the drone controller to control drone flight. All being accomplished, in real time, on an RPi4.

The adaption factor matrix is also learned during 2 NN training. And this is what’s used in the NF-Constant results below. But the key is that the linear factors (adaptation matrix) are updated (periodically) during actual drone flight by sampling the measured actual force and predicated force on the drone. The adaption matrix coefficients are updated using a least squares estimation fit.

In the reports supplemental information, the team showed a couple of state of the art adaptation approaches to problem of drone flight in wind. In the above chart the upper section is the x-axis wind effect and the lower portion is the z-axis wind effect and f (grey) is the actual force in that direction and f-hat (red) is the predicted force. The first column represents results from a normal integral controller. The next two columns are state of the art approaches (INDI and L1, see paper references) to the force prediction using adaptive control. If you look closely at these two columns, and compare the force prediction (in red) and the actual force (in grey), the force prediction always lags behind the actual force.

The next three columns show Neural-Fly constant (Neural-Fly with a constant adaptive control matrix, not being updated during flight), Neural-Fly-transfer (Using the NN trained on one drone and applying it’s adaptation to another drone in flight) and Neural-Fly. Neural-Fly constant also shows a lag between the predicted force and the actual force. But the Neural-Fly Transfer and Neural-Fly reduce this lag considerably.

The measurement for drone flight accuracy is tracking positional error. That is the difference between the desired position and its actual position over a number of trajectories. As shown in the chart tracking error decreased from 5.6cm to ~4 cm at a wind speed of 4.2m/s (15.1km/h or 9.3mph). Tracking error increases for wind speeds that were not used in training and for NF-transfer but in all wind speeds the tracking error is better with Neural-Fly than with any other approach.

Pretty impressive results from just using an RPi4.

[The Eds. would like to thank the CalTech team and especially Mike O’Connell for kindly answering our many questions on Neural-Fly.]

Picture Credit(s):

Living forever – the end of evolution part-3

Read an article yesterday on researchers who had been studying various mammals and trying to determine the number of DNA mutations they accumulate at about the time they die. The researchers found that after about 800 mutations for mole rats, they die, see Nature article Somatic mutation rates scale with lifespan across mammals and Telegraph article reporting on the research, Mystery of why humans die around 80 may finally be solved.

Similarly, at around 3500 mutations humans die, at around 3000 mutations dogs die and at around 1500 mutations mice die. But the real interesting thing is that the DNA mutation rates and mammal lifespan are highly (negatively) correlated. That is higher mutation rates lead to mammals with shorter life spans.

C. Linear regression of somatic substitution burden (corrected for analysable genome size) on individual age for dog, human, mouse and naked mole-rat samples. Samples from the same individual are shown in the same colour. Regression was performed using mean mutation burdens per individual. Shaded areas indicate 95% confidence intervals of the regression line. A shows microscopic images of sample mammalian cels and the DNA strands examined and B shows the distribution of different types of DNA mutations (substitutions or indels [insertion/deletions of DNA]).

The Telegraph article seems to imply that at 800 mutations all mammals die. But the Nature Article clearly indicates that death is at different mutation counts for each different type of mammal.

Such research show one way on how to live forever. We have talked about similar topics in the distant past see …-the end of evolution part 1 & part 2

But in any case it turns out that one of the leading factors that explains the average age of a mammal at death is its DNA mutation rate. Again, mammals with lower DNA mutation rates live longer on average and mammals with higher DNA mutation rates live shorter lives on average.

Moral of the story

if you want to live longer reduce your DNA mutation rates.

c, Zero-intercept LME regression of somatic mutation rate on inverse lifespan (1/lifespan), presented on the scale of untransformed lifespan (axis). For simplicity, the axis shows mean mutation rates per species, although rates per crypt were used in the regression. The darker shaded area indicates 95% CI of the regression line, and the lighter shaded area marks a twofold deviation from the line. Point estimate and 95% CI of the regression slope (k), FVE and range of end-of-lifespan burden are indicated.

All astronauts are subject to significant forms of cosmic radiation which can’t help but accelerate DNA mutations. So one would have to say that the risk of being an astronaut is that you will die younger.

Moon and Martian colonists will also have the same problem. People traveling, living and working there will have an increased risk of dying young. And of course anyone that works around radiation has the same risk.

Note, the mutation counts/mutation rates, that seem to govern life span are averages. Some individuals have lower mutation rates than their species and some (no doubt) have higher rates. These should have shorter and longer lives on average, respectively.

Given this variability in DNA mutation rates, I would propose that space agencies use as one selection criteria, the astronauts/colonists DNA mutation rate. So that humans which have lower than average DNA mutation rates have a higher priority of being selected to become astronauts/extra-earth colonists. One could using this research and assaying astronauts as they come back to earth for their DNA mutation counts, could theoretically determine the impact to their average life span.

In addition, most life extension research is focused on rejuvenating cellular or organism functionality, mainly through the use of young blood, other select nutrients, stem cells that target specific organs, etc. For example, see MIT Scientists Say They’ve Invented a Treatment That Reverses Hearing Loss which involves taking human cells, transform them into stem cells (at a certain maturity) and injecting them into the ear drum.

Living forever

In prior posts on this topic (see parts 1 &2 linked above) we suggested that with DNA computation and DNA storage (see or listen rather, to our GBoS podcast with CTO of Catalog) now becoming viable, one could potentially come up with a DNA program that could

  • Store an individuals DNA using some very reliable and long lived coding fashion (inside a cell or external to the cell) and
  • Craft a DNA program that could periodically be activated (cellular crontab) to access the stored DNA for the individual(in the cell would be easiest) and use this copy to replace/correct any DNA mutation throughout an individuals cells.

And we would need a very reliable and correct copy of that person’s DNA (using SHA256 hashing, CRCs, ECC, Parity and every other way to insure the DNA as captured is stored correctly forever). And the earlier we obtained the DNA copy for an individual human, the better.

Also, we would need a copy of the program (and probably the DNA) to be present in every cell in a human for this to work effectively. .

However, if we could capture a good copy of a person’s DNA early in their life we could, perhaps, sometime later, incorporate DNA code/program into the individual to use this copy and sweep through a person’s body (at that point in time) and correct any mutations that have accumulated to date. Ultimately, one could schedule this activity to occur like an annual checkup.

So yeah, life extension research can continue along the lines they are going and you can have a bunch of point solutions for cellular/organism malfunction OR it can focus on correctly copying and storing DNA forever and creating a DNA program that can correct DNA defects in every individual cell, using the stored DNA.

End of evolution

Yes mammals and that means any human could live forever this way. But it would signify the start of the end of evolution for the human species. That is whenever we captured their DNA copy, from that point on evolution (by mutating DNA) of that individual and any offspring of that individual could no longer take place. And if enough humans do this, throughout their lifespan, it means the end of evolution for humanity as a species

This assumes that evolution (which is natural variation driven by genetic mutation & survival of the fittest) requires DNA variation (essentially mutation) to drive the species forward.

~~~~

So my guess, is either we can live forever and stagnate as a species OR live normal lifespans and evolve as a species into something better over time. I believe nature has made it’s choice.

The surprising thing is that we are at a point in humanities existence where we can conceive of doing away with this natural process – evolution, forever.

Photo Credit(s):

Go big or go home for robust DNNs

Read a recent article Computer Scientists Prove why Bigger NNs do better discussing scientific research that proved a Universal Law of Robustness via Isoperimetry. This speaks to the perturbability of AI deep learning neural networks (DNN) and how not reduce it. But also applies to many other solutions to diverse multi-dimensional data problems.

Mathmatical Robustness

For AI ML DNN’s, we often witnesssupposedly well trained DNN models that do very well for classifications of examples of data similar to their training data but fail miserably on data that’s outside their training data.

Mathematicians call this attribute robustness and can measure this on a mapping function using a Lipschitz constant. One can consider this as a measure of variability of mapping from one set to another or in the case of DNNs, lack of robustness in classifications means they fail on relatively minor changes to input data.

Most serious AI researchers have empirically discovered that bigger DNNs work better and are more robust than smaller networks. There’s been somewhat of a conundrum as to why DNNs need to get bigger to properly generalize.

Universal Low of Robustness

What the researchers have proved is that in order to achieve some arbitrary level of robustness for a mapping function like DNNs, one needs many more parameters than expected the training data elements would indicate

For example, with the MNIST handwritten digit classification problem, models with 10**5 parameters to 10**6 parameters are required to achieve a 90% and 95% accuracy, respectively. But MNIST training data is 60K examples (10**4). Why should a MNIST DNN classification model need more than 10**4 parameters to achieve 100% accurate?

Author’s MNIST model with 688K parameters

From what we all learned in high school maths, to solve a function with N variables one needs N equations. This would lead one to believe that MNIST DNNs (essentially solving classification equations) should only need 60K or 10**4 parameters. But real DNNs to solve MNIST need more than that.

Looking at it in 2D. If one has two points, (x,y) for point A that maps to another (x,y) point B, one should only need to know one of the points and the slope of the line that connects them, or two parameters: point A (or B) and line slope.

Now with MNIST data that maps handwritten digits to one of 10 digits, we have essentially 10 possibilities being mapped from 60K samples. At best, we should need to know the 60K initial points in this image data space and their slope to the 10 digits they represent. Again something that approaches 60K pairs of parameters: one for the image point and one for the slope. But why doesn’t a MNIST model with 60K parameters achieve 100% accuracy.

I won’t claim to understand the math but what the researchers seem to be saying is that in order to have a relatively smooth mapping from the image space to the digit space one has to have 10**4 parameters X the dimensionality of the data. In this case, for MNIST, the dimensionality of the data is related to image size of 28X28, 0..255 grey scale pixel images. The image space alone would be on the order of 10**5. So multiplying this by the size of the training data, the researchers estimate that the number of parameters should be 10**9 to be 100% accurate.

Although, the researchers say that the data dimensionality of the MNIST images are probably not 10**5 (how they concluded this is not evident). As such, they believe one shouldn’t need 10**9 parameters to reach 100% proper classifications. They say it’s probably 1 or 2 orders of magnitude less, because not all of the image data space is populated. So if we use 10**3 as an estimate of the effective data dimensionality, they would estimate that one would need 10**7 parameter DNN to reach 100% accuracy on MNIST data.

The author’s MNIST model achieved a 99.2% accuracy after training for 15 Epochs, batch size=5. Although 688K parameters is not quite 10**6 parameters, it’s close. Unclear why one would need another factor of 10, but getting that extra 0.8% accuracy (to 100%) can be very difficult to achieve for any DNN model.

Another example, OpenAI’s GPT-3 NLP model

And OpenAI’s GPT-3 NLP model has 175B parameters. Their previous version, GPT-2, only had 1.5B parameters and they say that GPT-4 will have over a 100T parameters. The chart above shows accuracy stats for 3 versions of the GPT-3 model, one with 175B, one with 13B and another with 1.3B parameters.

According to OpenAI’s GPT-3 description, it can complete “almost any english language task” (text in ==> text out). This includes writing articles from a few prompts and text summarization.

GPT-3 was trained on almost 500B tokens (from web crawls to wikipedia dumps). Each token probably represents an english word or word phrase. According to the universal law, 175B parameters would not be sufficient. Probably why GPT-3 in the above chart didn’t reach 70%^ accuracy.

Probably would need at least another 3 orders of magnitude to get there or 175T parameters. Maybe with GPT-4, I can have it start writing my blog posts.

I don’t know about you, but I’m going to need more GPUs for my (home) AI lab.

Photo Credit(s)

Deepmind does code – part 1: the data

1st, let me express my and my fellow coders/programmers disappointment that Deepmind would take on coding. There are many other white collar work domains that need to be conquered before coding.

2nd, let me apologize for the lack of blog posts lately, all I can say is, business is picking up.

Saw an article over the last couple of weeks on Deepmind creating AlphaCode an artificial intelligence coding application which they used to enter coding contests and achieved an average 1238 rating or better than 54% of code contest participants.

I can’t recall where I first saw the news but Deepmind has a pretty decent blog post on AlphaCode and they have published a pre-print of their research paper on AlphaCode as well. I plan on discussing AlphaCode in detail over a couple of posts. This will be the first installment on where they got the data to train their models..

AlphaCode is a transformer-based language models (see: Wikipedia: Transformer (machine learning model) article) that translates a code competition problem statement into code, or a program that can when executed solve the problem statement. In order to train AlphaCode Deepmind first needed to obtain lots of source code.

It’s all about the (training) data

The first step in Deep Learning model generation is gathering data to train the model. Now where would Google’s Deepmind go to gather coding data – well GitHub, a public repository of all things software, of course.

They used GitHub data to pre-train their model(s) but also scraped code (problem statements & test cases) from published code contests to fine tune their model

Deepmind has released their fine-tuning, CodeContests training data for AlphaCode, on GitHub. So as to support other organiazations in creating AI models for coding.

GitHub source to the (pre-training) rescue

There are a couple of problems with using GitHub source code for training:

  • Github code is in any source code language the author feels most appropriate to use.
  • GitHub code is not guaranteed to work correctly.
  • GitHub code is not guaranteed to be completed code.
  • GitHub code represents a wide range of coding skill.
  • GitHub code doesn’t always come with a problem statement.

But the use of GitHub in their pre-training data set is intended to give their transformer-based language model some capability to understand (learn) what coding is all about, what a proper syntax would be, what a proper coding sequence would be, etc.

The AlphaCode team took a snapshot of selected git source repos. This meant they only scrapped Git repos that contained C++, C#, Go, Java, JavaScript, Lua, PHP, Python, Ruby, Rust, Scala, and TypeScript languages. They also dropped from pre-training data any source code with files larger than 1MB or that had any lines larger than 1000 characters. This was done to avoid using any machine generated code. They also stripped all the white space out of the selected source code files and compared them to eliminate all duplicated code.

Their final pre-training dataset was 715GB of data over 86 million source files.

Although, unstated, we would guess that the AlphaCode team used the GitHub repo’s README.md file as a surrogate for the solution description. Unclear what else could have been used unless they generated it automatically from extracting semantic content or generating a summarization of the README.md files.

Excerpt from Deepmind’s competitive code contest source code&problem statements README.md file

The (pre-)training data can be used to train a transformer-based language models. These are used today to provide language translation. In AlphaCode’s case they wanted to create, a code transformer-based model, that translates a specification of a coding problem into source code to solve that problem.

For language translation models, they use text files, in different languages, but represent the same law or information. and notably, are human generated translations.

One challenge with using internet scraped data for training is that it can easily contain actual solutions’ verbatim’ for the problems the model is trying to solve. In order to avoid copying these solutions entirely they decided to split their data into a training set, validation set and test set on a time basis. This way the training data used source code/problem statements only from a period of time prior to the validation set. Ditto for the training-validation data with the test data.

To show that this approach (using a time point to split the data) worked they trained a 1B parameter AlphaCode transformer on two different training-validation datasets, one where the validation data was selected at random (the normal approach to selecting validation data),, the “random” split and the other, with selecting validation data that only occurred some time after the training data, the “temporal’ split. The 1B AlphaCode transformer was able to properly code 0.8% of the problems using a 13K sample of 86M source files/problem statements on the random split, but only 0% on the temporal split.

So much for pre-training, let’s discuss fine tuning

AlphaCode was going to get nowhere with a 0% solve rate (ok this was based on a 13K sample and only a 1B parameter model) but they realized that Git code was only going to get them so far. (ok conjecture on my part)

So fine-tuning beyond pre-training (Git derived) data was needed. So the AlphaCode team turned to code competition source code/problem statement data.

Most code contests publish source code submissions as well as the problem statements and sample test cases. Bp scrapping these, Deepmind was able to attain a very well annotated dataset they could use to fine-tuning their AlphaCode transformer model.

They again used a temporal split for training/validation/test data. But they were also able to add metadata to their data that indicated whether the code solved the problem statement.

Code competitions also publish tests for the problem statement. Having the tests, a human can use them to validate whether their code at least works against the tests. Code contests also have a set of more (sophisticated) hidden tests that they use internally to validate code submissions.

This test data will become important later on in the models operation, which will be discussed in a future post, but suffice it to say that AlphaCode uses the public tests (and mutations of these) to validate AlphaCode generated source code before submitting them..

This fine-tuning dataset is available in the GitHub repo (linked to above) that Deepmind has created/curated for others to work with.

Another nicety of this fine-tuning data is they have proper, human created, problem statements to work from rather than README.md surrogates.

In part-2 we plan to describe the transformer-based model that was created for AlphaCode and at some point, discuss how they used testing in their code submissions.

Once again, all my information comes from Deepmind’s pre-print on their AlphaCode project (linked to above).

Any comments, please don’t hesitate to let me know.

Photo Credits:

AI navigation goes with the flow

Read an article the other day (Engineers Teach AI to Navigate Ocean with Minimal Energy) about a simulated robot that was trained to navigate 2D turbulent water flow to travel between locations. They used a combination reinforcement learning with a DNN derived policy. The article was reporting on a Nature Communications open access paper (Learning efficient navigation in vortical flow fields).

The team was attempting to create an autonomous probe that could navigate the ocean and other large bodies of water to gather information. I believe ultimately the intent was to provide the navigational smarts for a submersible that could navigate terrestrial and non-terrestrial oceans.

One of the biggest challenges for probes like this is to be able to navigate turbulent flow without needing a lot of propulsive power and using a lot of computational power. They said that any probe that could propel itself faster than the current could easily travel wherever it wanted but the real problem was to go somewhere with lower powered submersibles.. As a result, they set their probe to swim at a constant speed at 80% of the overall simulated water flow.

Even that was relatively feasible if you had unlimited computational power to train and inference with but trying to do this on something that could fit in a small submersible was a significant challenge. NLP models today have millions of parameters and take hours to train with multiple GPU/CPU cores in operation and lots of memory Inferencing using these NLP models also takes a lot of processing power.

The researchers targeted the computational power to something significantly smaller and wished to train and perform real time inferencing on the same hardware. They chose a “Teensy 4.0 micro-controller” board for their computational engine which costs under $20, had ~2MB of flash memory and fit in a space smaller than 1.5″x1.0″ (38.1mm X 25.4mm).

The simulation setup

The team started their probe turbulent flow training with a cylinder in a constant flow that generated downstream vortices, flowing in opposite directions. These vortices would travel from left to right in the simulated flow field. In order for the navigation logic to traverse this vortical flow, they randomly selected start and end locations on different sides.

The AI model they trained and used for inferencing was a combination of reinforcement learning (with an interesting multi-factor reward signal) and a policy using a trained deep neural network. They called this approach Deep RL.

For reinforcement learning, they used a reward signal that was a function of three variables: the time it took, the difference in distance to target and a success bonus if the probe reached the target. The time variable was a penalty and was the duration of the swim activity. Distance to target was how much the euclidean distance between the current probe location and the target location had changed over time. The bonus was only applied when the probe was in close proximity to the target location, The researchers indicated the reward signal could be used to optimize for other values such as energy to complete the trip, surface area traversed, wear and tear on propellers, etc.

For the reinforcement learning state information, they supplied the probe and the target relative location [Difference(Probe x,y, Target x,y)], And whatever sensor data being tested (e.g., for the velocity sensor equipped probe, the local velocity of the water at the probe’s location).

They trained the DNN policy using the state information (probe start and end location, local velocity/vorticity sensor data) to predict the swim angle used to navigate to the target. The DNN policy used 2 internal layers with 64 nodes each.

They benchmarked the Deep RL solution with local velocity sensing against a number of different approaches. One naive approach that always swam in the direction of the target, one flow blind approach that had no sensors but used feedback from it’s location changes to train with, one vorticity sensor approach which sensed the vorticity of the local water flow, and one complete knowledge approach (not shown above) that had information on the actual flow at every location in the 2D simulation

It turned out that of the first four (naive, flow-blind, vorticity sensor and velocity sensor) the velocity sensor configured robot had the highest success rate (“near 100%”).

That simulated probe was then measured against the complete flow knowledge version. The complete knowledge version had faster trip speeds, but only 18-39% faster (on the examples shown in the paper). However, the knowledge required to implement this algorithm would not be feasible in a real ocean probe.

More to be done

They tried the probes Deep RL navigation algorithm on a different simulated flow configuration, a double gyre flow field (sort of like 2 circular flows side by side but going in the opposite directions).

The previously trained (on cylinder vortical flow) Deep RL navigation algorithm only had a ~4% success rate with the double gyre flow. However, after training the Deep RL navigation algorithm on the double gyre flow, it was able to achieve a 87% success rate.

So with sufficient re-training it appears that the simulated probe’s navigation Deep RL could handle different types of 2D water flow.

The next question is how well their Deep RL can handle real 3D water flows, such as idal flows, up-down swells, long term currents, surface wind-wave effects, etc. It’s probable that any navigation for real world flows would need to have a multitude of Deep RL trained algorithms to handle each and every flow encountered in real oceans.

However, the fact that training and inferencing could be done on the same small hardware indicates that the Deep RL could possibly be deployed in any flow, let it train on the local flow conditions until success is reached and then let it loose, until it starts failing again. Training each time would take a lot of propulsive power but may be suitable for some probes.

The researchers have 3D printed a submersible with a Teensy microcontroller and an Arduino controller board with propellers surrounding it to be able to swim in any 3D direction. They have also constructed a water tank for use for in real life testing of their Deep RL navigation algorithms.

Picture credit(s):

DeepMind takes on poker & Scotland Yard

Read an article the other day (DeepMind makes bet on AI system that can play poker, chess, Go, and more) about a new DeepMind game playing program that used a new approach to taking on perfect and imperfect information games with the same algorithms.

As you may recall, DeepMind prior game playing programs, AlphaZero and MuZero played perfect information games chess, shoji, & Go and achieved top rankings in all of them. These were all based on reinforcement learning and advanced search. .

Perfect information games have no hidden information, that is all the information needed to play a game is visible to all players (see wikipedia Perfect information article). Imperfect information games have private or hidden information, only visible to one or a select set of players. In card playing, any card that’s not shown to all players, would represent hidden information. The other difference in imperfect games is that players attempt to keep their private information hidden as long as possible.

The latest DeepMind paper (see: Player of Games Arxiv paper) discusses a new approach to automated game playing that works for both perfect and imperfect information games. DeepMind’s latest game playing program is called Player of Games (PoG).

As many may know, Texas hold’em is a form of poker where everyone is dealt two cards down and five cards are dealt up, that everyone shares (see: Texas hold’em and Betting in poker articles on wikipedia). Betting happens after the two down cards are dealt, after the next 3 up cards (called the “flop”) are dealt, then after each of the remaining 2 up cards are dealt. Players select any of the (2 down and 5 up) cards to create the best 5 card poker hand. Betting is based on a blind (sort of minimal bet). PoG plays as a single player, performing all the betting as well as card playing for Texas hold’em. No limit betting says there’s no limit (maximum) to the amount of a bet in the game.

Scotland Yard is a board game where detectives chase down a criminal (Mr. X) on the run across the city of London (see wikipedia Scotland Yard (board game) article). Detectives each get 23 transportation tickets for taxies (11), busses (8), and underground trains (4). The game takes place on a board layout of London and starts with each detective and the criminal selecting a card with their hidden position on the board. The criminal gets (not quite, but almost) an unlimited amount of transportation tickets plus 5 (in USA) universal tickets (which can be used to take ferries as well as any other form of transport). Every time (except when using universal tickets) the criminal moves, he reveals his form of transportation. And 5 times during the game the criminal also reveals his current location. The detective that finds the criminal wins.

I assume all my readers know how to play chess and Go (or at least understand them).

While MuZero and AlphaZero used reinforcement learning for training and sophisticated search for in game play, PoG needed to do something different due to the imperfect (or hidden) information present in the hold’em and Scotland Yard games.

How PoG is different

In imperfect information games, it’s important to hide private information. In poker when I got a great hand, I raised my betting levels extensively. But this often caused my opponents to withdraw from betting unless they had a great hand as well. I sometimes think that if I were to bet more consistently and only at the last betting round, bet big when I have a good hand, I might win more $. No doubt, why I don’t play poker anymore.

Like AlphaZero and MuZero, PoG also uses reinforcement learning through self game play but adds something they call Counterfactual Regret (CFR) Minimization to their game trees.

In addition to normally selecting and computing a value (reward) for the optimal move as in reinforcement learning, PoG uses CFR minimization to compute values (rewards) for all moves not taken during every stage in a game, for each player. As such, PoG computes possible rewards for the optimal move at a stage (step, move) in a game plus the values for all the regret (counterfactual or other) moves for all players. CFR minimization attempts to minimize the regret move values and maximize move optimal values at each move, for each player in a game.

CFR minimization is used during training for a game in self-play as well as during actual game play to generate sub-trees from wherever the game happens to be. PoG uses a depth limited CFR minimization to generate game sub-trees during game play which helps to reduce the time it takes to determine the best move for all players. Read the ArXiv paper to learn more.

The challenge with this approach is that it will never be as good as pure reinforcement learning + advanced search for perfect games, such as chess and Go. For example, below we show Exploitability ratings for various PoG training levels for Leduc Poker and Scotland Yard. Exploitability levels are one way to measure how good the player is playing. Lower is better.

Perfect play (in an imperfect information game) would have an Exploitability of 0. The charts show that the more training done the better the game play by PoG for (Leduc) poker and Scotland Yard. (Leduc poker is a simplified poker game with 6 cards and limited betting).

On the other hand, for perfect games the results were ok, but not stellar. Scockfish is the current non-reinforcement learning, chess playing champion. Gnugo and Pachi are non-reinforcement learning, Go playing programs. In tables below, they use a relative ranking based on a 0 baseline for chess (Stockfish with 1 thread and 100msec think time) and Go (GnuGo). Higher is better.

~~~~

So, yes PoG can do well in imperfect information games with decent training and ok (but much much better than I and probably the vast majority of humans), in perfect information games.

Why concern ourselves with imperfect games, The world is chock full of imperfect information games. They seem to occur everywhere, military strategy, sport play, finance, etc. In fact, perfect games are the exception in real world situations. Thus, any advance to play multiple imperfect information games better is yet another small step towards AGI.

Photo Credit(s):

BEHAVIOR, an in-home robot, benchmark

As my readers probably already know, I’m a long time benchmark geek. So when I recently read an article out of Stanford (AI Experts Establish the “North Star” for Domestic Robotics Field) where a research team there developed a new robotic benchmark, I was interested. The new robotics benchmark is called BEHAVIOR which was documented in an ARXIV.org article (see: BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and ecOlogical enviRonments). It essentially uses real world data to identify domestic work activities that any robot would need to perform in a home.

The problems with robot benchmarks

The problem with benchmarks are multi-faceted:

  • How realistic are the workloads used to evaluate the systems being measured?
  • How accurate are the metrics used to rank and judge benchmark submissions?
  • How costly/complex is it to run a benchmark?
  • How are submissions audited and are they reproducible?.
  • Where are benchmark results reported and are they public?

And of course robotics brings in it’s own issues that makes benchmarking more difficult:

  • What sensors does the robot have to understand how to complete tasks?
  • What manipulators does the robot have to perform the tasks required of it?
  • Do the robots move in the environment and if so, how do the robots move?
  • Does the robot perform the task in the real world on in a simulated environment.

And of course, when using a simulated environment, how realistic is it.

BEHAVIOR with iGibson (see below) seem to answer many of these concerns for an in home robot benchmarking.

What is BEHAVIOR?

First, BEHAVIOR’s home making tasks were selected from an American Time Use Survey maintained by the USA Bureau of Labor Statistics which identifies tasks Americans perform in their homes. With BEHAVIOR 1.0 there are 100 tasks ranging from building a fruit basket to cleaning a toilet, and just about everything in between. I didn’t see any cooking or mixing drinks tasks but maybe those will be added.

Second, BEHAVIOR uses a predicate logic, called BDDL (BEHAVIOR Domain Definition Language) to define initial conditions for tasks such as tables, chairs, books, etc located in the room, where objects need to be placed, and successful completion goals or what task completion should look like.

BEHAVIOR uses 15 different rooms or scenes in their benchmark, such as a kitchen, garage, study, etc. Each of the 100 tasks are performed in a specific room.

BEHAVIOR incorporates 1217 different objects in 391 categories. Once initial conditions are defined for a task, BEHAVIOR essentially randomly selects different object for the task and randomly locates them throughout the room.

In order to run the benchmark, one could conceivably create a real room, with all the objects and have them placed according to BEHAVIOR BDDL’s randomly assigned locations with a robot physically present in the room and have it perform the assigned task OR one could use a simulation engine and have the robot run the task in the simulation environment, with simulated room, objects and robot.

It appears as if BEHAVIOR could operate in any robotics simulation environment but has been currently implemented in Stanford’s open source robotics simulation engine called iGibson 2.0 (see: iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks and iGibson 2.0 website). iGibson uses the Bullet real time physics engine for realistic physical environment simulation.

A robot operating within iGibson is provided a 3D rendering of the room and objects in images or LIDAR sensor scans. It can then identify the objects that it needs to manipulate to perform the tasks. One can define the robot simulated sensors and manipulators in iGibnot 2.0 and it’s written in Python, is open source (GitHub Repo) and can be installed to run on (Ubuntu 16.04) Linux, Windows (10) or Mac (10.15) systems.

Finally, BEHAVIOR uses a set of metrics to determine how well a robot has performed its assigned task. Their first metric is success score defined as the fraction of goal conditions satisfied by the robot performing the task. Such as the number of dishes properly cleaned and placed in the drying rack divided by the total number of dishes for a “washing dishes” task. And their second metric is a set of efficiency metrics, like time to complete a task, sum total of object distance moved during the task, how well objects are arranged at task completion (is the toilet seat down…), etc.

Another feature of iGibson 2.0 is that it offers the ability to record a human (in VR) doing a task in its simulated environment. So if your robotic system is able to learn by example, then iGibson could be used to provide training data for an activity.

~~~~

A couple of additions to the BEHAVIOR benchmark/iGibson simulation environment that I would like to see:

  • There ought to be a way to construct a house/apartment where multiple rooms are arranged in a hierarchy, i.e., rooms associated with floors with connections using hallways, doors, stairs, etc. between them. This way one could conceivably have a define a set of homes/apartments (let’s say 5) that a robot would perform its tasks in.
  • They need a task list to drive robot activities. Assume that there’s some amount of time let’s say 8-12 hours that a robot is active and construct a series of tasks that need to be accomplished during that period.
  • Robots should be placed in the rooms/apartments/homes at random with random orientation and then they would have to navigate through rooms/passageways to the rooms to perform the tasks.
  • They need to add pet/human avatars in the rooms throughout a home. These would represent real time obstacles to task completion/navigation as well as add more tasks associated with caring for pets/humans.
  • They need the ability to add non-home rooms that could encompass factory floors, emergency response debris fields, grocery stores, etc. and their own unique set of tasks for each of these so that it could be used as a benchmark for more than just domestic robots.

Aside from the above additions to BEHAVIOR/iGibson 2.0, there’s the question of the organization that manages the benchmark and submissions. There needs to be a website/place to publish benchmark results for a robot AND a mechanism to audit results for accuracy to insure fair play.

Typically this would be associated with an organization responsible for publishing and auditing submissions as well as guide further development of BEHAVIOR/iGibson 2.0. BEHAVIOR 1.0 is not the end but it’s a great start at providing realistic tasks that any domestic robot would need to perform. 

Benchmarks have always aided the development and assessment of new technologies. Having a in home robot benchmark like BEHAVIOR makes getting domestic robots that do what we want them to do a more likely possibility someday.

There’s a new benchmark in town and it signals the dawning of the domestic robot age.

Photo Credit(s):