Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
This work addresses the efficiency and performance of offline RL algorithms, which is an incremental improvement for researchers and practitioners in data-driven reinforcement learning.
The paper tackles the problem of overlooked data sampling techniques in offline reinforcement learning by proposing Prioritized Trajectory Replay, a memory technique that extends sampling to trajectories for better information extraction from limited data, demonstrating benefits when integrated with existing algorithms on the D4RL benchmark.
In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL has been overlooked despite its potential to enhance online RL performance. Recent research suggests applying sampling techniques directly to state-transitions does not consistently improve performance in offline RL. Therefore, in this study, we propose a memory technique, (Prioritized) Trajectory Replay (TR/PTR), which extends the sampling perspective to trajectories for more comprehensive information extraction from limited data. TR enhances learning efficiency by backward sampling of trajectories that optimizes the use of subsequent state information. Building on TR, we build the weighted critic target to avoid sampling unseen actions in offline training, and Prioritized Trajectory Replay (PTR) that enables more efficient trajectory sampling, prioritized by various trajectory priority metrics. We demonstrate the benefits of integrating TR and PTR with existing offline RL algorithms on D4RL. In summary, our research emphasizes the significance of trajectory-based data sampling techniques in enhancing the efficiency and performance of offline RL algorithms.