Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset
This work addresses a key, underexplored problem in offline RL for researchers and practitioners by providing a method to enhance training efficiency and performance, though it is incremental as it builds on existing actor-critic and optimization techniques.
The paper tackles the challenge of selecting optimal subsets from offline reinforcement learning datasets to improve performance and efficiency, introducing ReDOR, which frames this as a gradient approximation problem and uses modified orthogonal matching pursuit, resulting in boosted algorithm performance with lower computational complexity.
Offline reinforcement learning (RL) represents a significant shift in RL research, allowing agents to learn from pre-collected datasets without further interaction with the environment. A key, yet underexplored, challenge in offline RL is selecting an optimal subset of the offline dataset that enhances both algorithm performance and training efficiency. Reducing dataset size can also reveal the minimal data requirements necessary for solving similar problems. In response to this challenge, we introduce ReDOR (Reduced Datasets for Offline RL), a method that frames dataset selection as a gradient approximation optimization problem. We demonstrate that the widely used actor-critic framework in RL can be reformulated as a submodular optimization objective, enabling efficient subset selection. To achieve this, we adapt orthogonal matching pursuit (OMP), incorporating several novel modifications tailored for offline RL. Our experimental results show that the data subsets identified by ReDOR not only boost algorithm performance but also do so with significantly lower computational complexity.