Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning

Offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance by leveraging pre-collected data and meta-learning techniques. Previous context-based approaches predominantly rely on the intuition that alternating optimization between the context encoder and the policy can lead to performance improvements, as long as the context encoder follows the principle of maximizing the mutual information between the task and the task representation ($I(Z;M)$) while the policy adopts the standard offline reinforcement learning (RL) algorithms conditioning on the learned task representation. Despite promising results, the theoretical justification of performance improvements for such intuition remains underexplored. Inspired by the return discrepancy scheme in the model-based RL field, we find that the previous optimization framework can be linked with the general RL objective of maximizing the expected return, thereby providing a feasible explanation concerning performance improvements. Furthermore, after scrutinizing this optimization framework, we find it ignores the impacts stemming from the variation of the task representation in the alternating optimization process, which may lead to performance improvement collapse. We name this issue \underline{task representation shift} and theoretically prove that the monotonic performance improvements can be guaranteed with appropriate context encoder updates. We set different manners to rein in the task representation shift on three widely adopted training objectives concerning maximizing $I(Z;M)$ across different data qualities. Empirical results show that reining in the task representation shift can indeed improve performance. Our work opens up a new avenue for OMRL, leading to a better understanding between the performance and the task representation.