相关论文: Understanding Goal Generalisation in Sequential Re…

We consider learning from labeled data collected across multiple environments, where the data distribution may vary across these environments. This problem is commonly approached from a causal perspective, seeking invariant representations…

In the zero-shot policy transfer setting in reinforcement learning, the goal is to train an agent on a fixed set of training environments so that it can generalise to similar, but unseen, testing environments. Previous work has shown that…

Offline reinforcement learning (RL) have received rising interest due to its appealing data efficiency. The present study addresses behavior estimation, a task that lays the foundation of many offline RL algorithms. Behavior estimation aims…

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…

Building autonomous machines that can explore open-ended environments, discover possible interactions and build repertoires of skills is a general objective of artificial intelligence. Developmental approaches argue that this can only be…

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Generalizability of Reinforcement Learning (RL) agents (ability to perform on environments different from the ones they have been trained on) is a key problem as agents have the tendency to overfit to their training environments. In order…

While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of distribution shift is goal misgeneralization, where the agent…

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

Recent improvements in conditional generative modeling have made it possible to generate high-quality images from language descriptions alone. We investigate whether these methods can directly address the problem of sequential…

Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated…

A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing on-policy updates with respect to the commanded goal.…

The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined…

Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a…

We show that iterative deployment of large language models (LLMs), each fine-tuned on data carefully curated by users from the previous models' deployment, can significantly change the properties of the resultant models. By testing this…

We address the problem of building agents whose goal is to learn to execute out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that…

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction…

Reinforcement learning (RL) has achieved remarkable success in a wide range of sequential decision-making problems. Recent diffusion-based policies further improve RL by modeling complex, high-dimensional action distributions. However,…

Single-task RL agents are typically trained under a fixed reward function, which limits their robustness to reward misspecification and their ability to adapt to changing preferences. We introduce Reward-Conditioned Reinforcement Learning…

We study the scalable multi-agent reinforcement learning (MARL) with general utilities, defined as nonlinear functions of the team's long-term state-action occupancy measure. The objective is to find a localized policy that maximizes the…