Related papers: Provably Efficient Causal Model-Based Reinforcemen…

Reinforcement learning is commonly concerned with problems of maximizing accumulated rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the state space attain maximal reward. In such a case, the…

To safely and efficiently solve motion planning problems in multi-agent settings, most approaches attempt to solve a joint optimization that explicitly accounts for the responses triggered in other agents. This often results in solutions…

Traditional approaches to the design of multi-agent navigation algorithms consider the environment as a fixed constraint, despite the obvious influence of spatial constraints on agents' performance. Yet hand-designing improved environment…

What can be learned about causality and experimentation from passive data? This question is salient given recent successes of passively-trained language models in interactive domains such as tool use. Passive learning is inherently limited.…

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to…

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by…

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

Learning policies which are robust to changes in the environment are critical for real world deployment of Reinforcement Learning agents. They are also necessary for achieving good generalization across environment shifts. We focus on…

Data collection has become an increasingly important problem in robotic manipulation, yet there still lacks much understanding of how to effectively collect data to facilitate broad generalization. Recent works on large-scale robotic data…

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…

A key challenge for the safety of advanced AI systems is the possibility that multiple simpler agents might inadvertently form a collective agent with capabilities and goals distinct from those of any individual. More generally, determining…

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the…

Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within a particular framework, every almost optimal and general…

Reinforcement Learning agents are expected to eventually perform well. Typically, this takes the form of a guarantee about the asymptotic behavior of an algorithm given some assumptions about the environment. We present an algorithm for a…

Many reinforcement learning (RL) environments consist of independent entities that interact sparsely. In such environments, RL agents have only limited influence over other entities in any particular situation. Our idea in this work is that…

Inverse reinforcement learning methods aim to retrieve the reward function of a Markov decision process based on a dataset of expert demonstrations. The commonplace scarcity and heterogeneous sources of such demonstrations can lead to the…

One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks. However, the generalization ability of model-based agents…

It is evidence that representation learning can improve model's performance over multiple downstream tasks in many real-world scenarios, such as image classification and recommender systems. Existing learning approaches rely on establishing…

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…