Estimating the fatality rate is difficult but doable with better data

    

The case fatality rate quantifies how dangerous COVID-19 is, and how risk of death varies with strata like geography, age, and race. Current estimates of the COVID-19 case fatality rate (CFR) are biased for dozens of reasons, from under-testing of asymptomatic cases to government misreporting. We provide a careful and comprehensive overview of these biases and show how statistical thinking and modeling can combat such problems. Most importantly, data quality is key to unbiased CFR estimation. We show that a relatively small dataset collected via careful contact tracing would enable simple and potentially more accurate CFR estimation.

Continue

Exploring Exploration: Comparing Children with RL Agents in Unified Environments

    

Despite recent advances in artificial intelligence (AI) research, human children are still by far the best learners we know of, learning impressive skills like language and high-level reasoning from very little data. Children’s learning is supported by highly efficient, hypothesis-driven exploration: in fact, they explore so well that many machine learning researchers have been inspired to put videos like the one below in their talks to motivate research into exploration methods. However, because applying results from studies in developmental psychology can be difficult, this video is often the extent to which such research actually connects with human cognition.


A time-lapse of a baby playing with toys. Source.

Continue

Can RL From Pixels be as Efficient as RL From State?

    

A remarkable characteristic of human intelligence is our ability to learn tasks quickly. Most humans can learn reasonably complex skills like tool-use and gameplay within just a few hours, and understand the basics after only a few attempts. This suggests that data-efficient learning may be a meaningful part of developing broader intelligence.

On the other hand, Deep Reinforcement Learning (RL) algorithms can achieve superhuman performance on games like Atari, Starcraft, Dota, and Go, but require large amounts of data to get there. Achieving superhuman performance on Dota took over 10,000 human years of gameplay. Unlike simulation, skill acquisition in the real-world is constrained to wall-clock time. In order to see similar breakthroughs to AlphaGo in real-world settings, such as robotic manipulation and autonomous vehicle navigation, RL algorithms need to be data-efficient — they need to learn effective policies within a reasonable amount of time.


To date, it has been commonly assumed that RL operating on coordinate state is significantly more data-efficient than pixel-based RL. However, coordinate state is just a human crafted representation of visual information. In principle, if the environment is fully observable, we should also be able to learn representations that capture the state.

Continue

Decentralized Reinforcement Learning:
Global Decision-Making via
Local Economic Transactions

    

Many neural network architectures that underlie various artificial intelligence systems today bear an interesting similarity to the early computers a century ago. Just as early computers were specialized circuits for specific purposes like solving linear systems or cryptanalysis, so too does the trained neural network generally function as a specialized circuit for performing a specific task, with all parameters coupled together in the same global scope.

One might naturally wonder what it might take for learning systems to scale in complexity in the same way as programmed systems have. And if the history of how abstraction enabled computer science to scale gives any indication, one possible place to start would be to consider what it means to build complex learning systems at multiple levels of abstraction, where each level of learning is the emergent consequence of learning from the layer below.

This post discusses our recent paper that introduces a framework for societal decision-making, a perspective on reinforcement learning through the lens of a self-organizing society of primitive agents. We prove the optimality of an incentive mechanism for engineering the society to optimize a collective objective. Our work also provides suggestive evidence that the local credit assignment scheme of the decentralized reinforcement learning algorithms we develop to train the society facilitates more efficient transfer to new tasks.

Continue

D4RL: Building Better Benchmarks for Offline Reinforcement Learning

    

In the last decade, one of the biggest drivers for success in machine learning has arguably been the rise of high-capacity models such as neural networks along with large datasets such as ImageNet to produce accurate models. While we have seen deep neural networks being applied to success in reinforcement learning (RL) in domains such as robotics, poker, board games, and team-based video games, a significant barrier to getting these methods working on real-world problems is the difficulty of large-scale online data collection. Not only is online data collection time-consuming and expensive, it can also be dangerous in safety-critical domains such as driving or healthcare. For example, it would be unreasonable to allow reinforcement learning agents to explore, make mistakes, and learn while controlling an autonomous vehicle or treating patients in a hospital. This makes learning from pre-collected experience enticing, and we are fortunate in that many of these domains, there already exist large datasets for applications such as self-driving cars, healthcare, or robotics. Therefore, the ability for RL algorithms to learn offline from these datasets (a setting referred to as offline or batch RL) has an enormous potential impact in shaping the way we build machine learning systems for the future.

Continue

Open Compound Domain Adaptation

    

The World is Continuously Varying

Imagine we want to train a self-driving car in New York so that we can take it all the way to Seattle without tediously driving it for over 48 hours. We hope our car can handle all kinds of environments on the trip and send us safely to the destination. We know that road conditions and views can be very different. It is intuitive to simply collect road data of this trip, let the car learn from every possible condition, and hope it becomes the perfect self-driving car for our New York to Seattle trip. It needs to understand the traffic and skyscrapers in big cities like New York and Chicago, more unpredictable weather in Seattle, mountains and forests in Montana, and all kinds of country views, farmlands, animals, etc. However, how much data is enough? How many cities should we collect data from? How many weather conditions should we consider? We never know, and these questions never stop.


Figure 1: Domains boundaries are rarely clear. Therefore, it is hard to set up definite domain descriptions for all possible domains.

Continue

OmniTact: A Multi-Directional High-Resolution Touch Sensor

    


Human thumb next to our OmniTact sensor, and a US penny for scale.

Touch has been shown to be important for dexterous manipulation in robotics. Recently, the GelSight sensor has caught significant interest for learning-based robotics due to its low cost and rich signal. For example, GelSight sensors have been used for learning inserting USB cables (Li et al, 2014), rolling a die (Tian et al. 2019) or grasping objects (Calandra et al. 2017).

The reason why learning-based methods work well with GelSight sensors is that they output high-resolution tactile images from which a variety of features such as object geometry, surface texture, normal and shear forces can be estimated that often prove critical to robotic control. The tactile images can be fed into standard CNN-based computer vision pipelines allowing the use of a variety of different learning-based techniques: In Calandra et al. 2017 a grasp-success classifier is trained on GelSight data collected in self-supervised manner, in Tian et al. 2019 Visual Foresight, a video-prediction-based control algorithm is used to make a robot roll a die purely based on tactile images, and in Lambeta et al. 2020 a model-based RL algorithm is applied to in-hand manipulation using GelSight images.

Unfortunately applying GelSight sensors in practical real-world scenarios is still challenging due to its large size and the fact that it is only sensitive on one side. Here we introduce a new, more compact tactile sensor design based on GelSight that allows for omnidirectional sensing, i.e. making the sensor sensitive on all sides like a human finger, and show how this opens up new possibilities for sensorimotor learning. We demonstrate this by teaching a robot to pick up electrical plugs and insert them purely based on tactile feedback.

Continue

Four Novel Approaches to Manipulating Fabric using Model-Free and Model-Based Deep Learning in Simulation

    


Humans manipulate 2D deformable structures such as fabric on a daily basis, from putting on clothes to making beds. Can robots learn to perform similar tasks? Successful approaches can advance applications such as dressing assistance for senior care, folding of laundry, fabric upholstery, bed-making, manufacturing, and other tasks. Fabric manipulation is challenging, however, because of the difficulty in modeling system states and dynamics, meaning that when a robot manipulates fabric, it is hard to predict the fabric’s resulting state or visual appearance.

In this blog post, we review four recent papers from two research labs (Pieter Abbeel’s and Ken Goldberg’s) at Berkeley AI Research (BAIR) that investigate the following hypothesis: is it possible to employ learning-based approaches to the problem of fabric manipulation?

We demonstrate promising results in support of this hypothesis by using a variety of learning-based methods with fabric simulators to train smoothing (and even folding) policies in simulation. We then perform sim-to-real transfer to deploy the policies on physical robots. Examples of the learned policies in action are shown in the GIFs above.

We show that deep model-free methods trained from exploration or from demonstrations work reasonably well for specific tasks like smoothing, but it is unclear how well they generalize to related tasks such as folding. On the other hand, we show that deep model-based methods have more potential for generalization to a variety of tasks, provided that the learned models are sufficiently accurate. In the rest of this post, we summarize the papers, emphasizing the techniques and tradeoffs in each approach.

Continue

Unsupervised Meta-Learning: Learning to Learn without Supervision

    

This post is cross-listed on the CMU ML blog.

The history of machine learning has largely been a story of increasing abstraction. In the dawn of ML, researchers spent considerable effort engineering features. As deep learning gained popularity, researchers then shifted towards tuning the update rules and learning rates for their optimizers. Recent research in meta-learning has climbed one level of abstraction higher: many researchers now spend their days manually constructing task distributions, from which they can automatically learn good optimizers. What might be the next rung on this ladder? In this post we introduce theory and algorithms for unsupervised meta-learning, where machine learning algorithms themselves propose their own task distributions. Unsupervised meta-learning further reduces the amount of human supervision required to solve tasks, potentially inserting a new rung on this ladder of abstraction.

Continue

The Ingredients of Real World Robotic Reinforcement Learning

    


Robots have been useful in environments that can be carefully controlled, such as those commonly found in industrial settings (e.g. assembly lines). However, in unstructured settings like the home, we need robotic systems that are adaptive to the diversity of the real world.

Continue