We propose a method for meta-learning reinforcement learning algorithms by searching over the space of computational graphs which compute the loss function for a value-based model-free RL agent to optimize. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. Our method can both learn from scratch and bootstrap off known existing algorithms, like DQN, enabling interpretable modifications which improve performance. Learning from scratch on simple classical control and gridworld tasks, our method rediscovers the temporal-difference (TD) algorithm. Bootstrapped from DQN, we highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games. The analysis of the learned algorithm behavior shows resemblance to recently proposed RL algorithms that address overestimation in value-based methods.
A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a challenging problem, particularly when hand-engineered reward functions are not available. Learned dynamics models are a promising approach for learning about the environment without rewards or task-directed data, but planning to reach goals with such a model requires a notion of functional similarity between observations and goal states. We present a self-supervised method for model-based visual goal reaching, which uses both a visual dynamics model as well as a dynamical distance function learned using model-free reinforcement learning. Our approach learns entirely using offline, unlabeled data, making it practical to scale to large and diverse datasets. In our experiments, we find that our method can successfully learn models that perform a variety of tasks at test-time, moving objects amid distractors with a simulated robotic arm and even learning to open and close a drawer using a real-world robot. In comparisons, we find that this approach substantially outperforms both model-free and model-based prior methods. Videos and visualizations are available here: http://sites.google.com/berkeley.edu/mbold.
We propose a learning-based navigation system for reaching visually indicated goals and demonstrate this system on a real mobile robot platform. Learning provides an appealing alternative to conventional methods for robotic navigation: instead of reasoning about environments in terms of geometry and maps, learning can enable a robot to learn about navigational affordances, understand what types of obstacles are traversable (e.g., tall grass) or not (e.g., walls), and generalize over patterns in the environment. However, unlike conventional planning algorithms, it is harder to change the goal for a learned policy during deployment. We propose a method for learning to navigate towards a goal image of the desired destination. By combining a learned policy with a topological graph constructed out of previously observed data, our system can determine how to reach this visually indicated goal even in the presence of variable appearance and lighting. Three key insights, waypoint proposal, graph pruning and negative mining, enable our method to learn to navigate in real-world environments using only offline data, a setting where prior methods struggle. We instantiate our method on a real outdoor ground robot and show that our system, which we call ViNG, outperforms previously-proposed methods for goal-conditioned reinforcement learning, including other methods that incorporate reinforcement learning and search. We also study how ViNG generalizes to unseen environments and evaluate its ability to adapt to such an environment with growing experience. Finally, we demonstrate ViNG on a number of real-world applications, such as last-mile delivery and warehouse inspection. We encourage the reader to check out the videos of our experiments and demonstrations at our project website https://sites.google.com/view/ving-robot
Few-shot meta-learning methods consider the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks. However, in many real world settings, it is more natural to view the problem as one of minimizing the total amount of supervision --- both the number of examples needed to learn a new task and the amount of data needed for meta-learning. Such a formulation can be studied in a sequential learning setting, where tasks are presented in sequence. When studying meta-learning in this online setting, a critical question arises: can meta-learning improve over the sample complexity and regret of standard empirical risk minimization methods, when considering both meta-training and adaptation together? The answer is particularly non-obvious for meta-learning algorithms with complex bi-level optimizations that may demand large amounts of meta-training data. To answer this question, we extend previous meta-learning algorithms to handle the variable-shot settings that naturally arise in sequential learning: from many-shot learning at the start, to zero-shot learning towards the end. On sequential learning problems, we find that meta-learning solves the full task set with fewer overall labels and achieves greater cumulative performance, compared to standard supervised methods. These results suggest that meta-learning is an important ingredient for building learning systems that continuously learn and improve over a sequence of problems.
Distribution shifts can cause significant degradation in a broad range of machine learning (ML) systems deployed in the wild. However, many widely-used datasets in the ML community today were not designed for evaluating distribution shifts. These datasets typically have training and test sets drawn from the same distribution, and prior work on retrofitting them with distribution shifts has generally relied on artificial shifts that need not represent the kinds of shifts encountered in the wild. In this paper, we present WILDS, a benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications, from tumor identification to wildlife monitoring to poverty mapping. WILDS builds on top of recent data collection efforts by domain experts in these applications and provides a unified collection of datasets with evaluation metrics and train/test splits that are representative of real-world distribution shifts. These datasets reflect distribution shifts arising from training and testing on different hospitals, cameras, countries, time periods, demographics, molecular scaffolds, etc., all of which cause substantial performance drops in our baseline models. Finally, we survey other applications that would be promising additions to the benchmark but for which we did not manage to find appropriate datasets; we discuss their associated challenges and detail datasets and shifts where we did not see an appreciable performance drop. By unifying datasets from a variety of application areas and making them accessible to the ML community, we hope to encourage the development of general-purpose methods that are anchored to real-world distribution shifts and that work well across different applications and problem settings. Data loaders, default models, and leaderboards are available at https://wilds.stanford.edu.
Model-based reinforcement learning (MBRL) methods have shown strong sample efficiency and performance across a variety of tasks, including when faced with high-dimensional visual observations. These methods learn to predict the environment dynamics and expected reward from interaction and use this predictive model to plan and perform the task. However, MBRL methods vary in their fundamental design choices, and there is no strong consensus in the literature on how these design decisions affect performance. In this paper, we study a number of design decisions for the predictive model in visual MBRL algorithms, focusing specifically on methods that use a predictive model for planning. We find that a range of design decisions that are often considered crucial, such as the use of latent spaces, have little effect on task performance. A big exception to this finding is that predicting future observations (i.e., images) leads to significant task performance improvement compared to only predicting rewards. We also empirically find that image prediction accuracy, somewhat surprisingly, correlates more strongly with downstream task performance than reward prediction accuracy. We show how this phenomenon is related to exploration and how some of the lower-scoring models on standard benchmarks (that require exploration) will perform the same as the best-performing models when trained on the same training data. Simultaneously, in the absence of exploration, models that fit the data better usually perform better on the downstream task as well, but surprisingly, these are often not the same models that perform the best when learning and exploring from scratch. These findings suggest that performance and exploration place important and potentially contradictory requirements on the model.
A wide range of reinforcement learning (RL) problems - including robustness, transfer learning, unsupervised RL, and emergent complexity - require specifying a distribution of tasks or environments in which a policy will be trained. However, creating a useful distribution of environments is error prone, and takes a significant amount of developer time and effort. We propose Unsupervised Environment Design (UED) as an alternative paradigm, where developers provide environments with unknown parameters, and these parameters are used to automatically produce a distribution over valid, solvable environments. Existing approaches to automatically generating environments suffer from common failure modes: domain randomization cannot generate structure or adapt the difficulty of the environment to the agent's learning progress, and minimax adversarial training leads to worst-case environments that are often unsolvable. To generate structured, solvable environments for our protagonist agent, we introduce a second, antagonist agent that is allied with the environment-generating adversary. The adversary is motivated to generate environments which maximize regret, defined as the difference between the protagonist and antagonist agent's return. We call our technique Protagonist Antagonist Induced Regret Environment Design (PAIRED). Our experiments demonstrate that PAIRED produces a natural curriculum of increasingly complex environments, and PAIRED agents achieve higher zero-shot transfer performance when tested in highly novel environments.
Reinforcement learning provides a general framework for flexible decision making and control, but requires extensive data collection for each new task that an agent needs to learn. In other machine learning fields, such as natural language processing or computer vision, pre-training on large, previously collected datasets to bootstrap learning for new tasks has emerged as a powerful paradigm to reduce data requirements when learning a new task. In this paper, we ask the following question: how can we enable similarly useful pre-training for RL agents? We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials from a wide range of previously seen tasks, and we show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors. We demonstrate the effectiveness of our approach in challenging robotic manipulation domains involving image observations and sparse reward functions, where our method outperforms prior works by a substantial margin.
We study the problem of predicting and controlling the future state distribution of an autonomous agent. This problem, which can be viewed as a reframing of goal-conditioned reinforcement learning (RL), is centered around learning a conditional probability density function over future states. Instead of directly estimating this density function, we indirectly estimate this density function by training a classifier to predict whether an observation comes from the future. Via Bayes' rule, predictions from our classifier can be transformed into predictions over future states. Importantly, an off-policy variant of our algorithm allows us to predict the future state distribution of a new policy, without collecting new experience. This variant allows us to optimize functionals of a policy's future state distribution, such as the density of reaching a particular goal state. While conceptually similar to Q-learning, our work lays a principled foundation for goal-conditioned RL as density estimation, providing justification for goal-conditioned methods used in prior work. This foundation makes hypotheses about Q-learning, including the optimal goal-sampling ratio, which we confirm experimentally. Moreover, our proposed method is competitive with prior goal-conditioned RL methods.
Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that are needed for robots to generalize broadly. Videos of humans, on the other hand, are a readily available source of broad and interesting experiences. In this paper, we consider the question: can we perform reinforcement learning directly on experience collected by humans? This problem is particularly difficult, as such videos are not annotated with actions and exhibit substantial visual domain shift relative to the robot's embodiment. To address these challenges, we propose a framework for reinforcement learning with videos (RLV). RLV learns a policy and value function using experience collected by humans in combination with data collected by robots. In our experiments, we find that RLV is able to leverage such videos to learn challenging vision-based skills with less than half as many samples as RL methods that learn from scratch.