Improving Zero-Shot Offline RL via Behavioral Task Sampling
Addresses a key bottleneck in offline zero-shot RL for practitioners needing agents that generalize to unseen tasks without environment interaction.
Offline zero-shot RL struggles with random task sampling. The authors propose extracting task vectors from the offline dataset, improving zero-shot performance by an average of 20% across benchmarks.
Offline zero-shot reinforcement learning (RL) aims to learn agents that optimize unseen reward functions without additional environment interaction. The standard approach to this problem trains task-conditioned policies by sampling task vectors that define linear reward functions over learned state representations. In most existing algorithms, these task vectors are randomly sampled, implicitly assuming this adequately captures the structure of the task space. We argue that doing so leads to suboptimal zero-shot generalization. To address this limitation, we propose extracting task vectors directly from the offline dataset and using them to define the task distribution used for policy training. We introduce a simple and general reward function extraction procedure that integrates into existing offline zero-shot RL algorithms. Across multiple benchmark environments and baselines, our approach improves zero-shot performance by an average of 20%, highlighting the importance of principled task sampling in offline zero-shot RL.