On Context Distribution Shift in Task Representation Learning for Offline Meta RL
This work addresses a specific challenge in offline meta RL for robotics or simulation domains, representing an incremental improvement over existing methods.
The paper tackles the problem of context distribution shift in offline meta reinforcement learning, where the context encoder trained on offline datasets fails to generalize to new tasks due to distribution mismatch. The proposed hard-sampling-based strategy yields more robust task representations and improves testing performance, as shown by higher accumulated returns in continuous control tasks.
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently adapt the agent to new tasks by inferring the task representation, and then adjusting the policy based on this inferred representation. In this work, we focus on context-based OMRL, specifically on the challenge of learning task representation for OMRL. We conduct experiments that demonstrate that the context encoder trained on offline datasets might encounter distribution shift between the contexts used for training and testing. To overcome this problem, we present a hard-sampling-based strategy to train a robust task context encoder. Our experimental findings on diverse continuous control tasks reveal that utilizing our approach yields more robust task representations and better testing performance in terms of accumulated returns compared to baseline methods. Our code is available at https://github.com/ZJLAB-AMMI/HS-OMRL.