With the widespread adoption of deep learning, reinforcement learning (RL) has
experienced a dramatic increase in popularity, scaling to previously intractable problems …

Reinforcement learning (RL) interacts with the environment to solve sequential decision-
making problems via a trial-and-error approach. Errors are always undesirable in real-world …

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data.
Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms …

Offline reinforcement learning (RL) defines the task of learning from a static logged dataset
without continually interacting with the environment. The distribution shift between the …

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy
optimization from large pre-recorded datasets without online environment interaction. It …

Most prior approaches to offline reinforcement learning (RL) have taken an iterative actor-
critic approach involving off-policy evaluation. In this paper we show that simply doing one …

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …

We show that domain-general automatic evaluators can significantly improve the
performance of agents for web navigation and device control. We experiment with multiple …

In offline reinforcement learning, weighted regression is a common method to ensure the
learned policy stays close to the behavior policy and to prevent selecting out-of-sample …

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional
policy produces promising results. The Decision Transformer (DT) combines the conditional …