CausalCOMRL: Context-Based Offline Meta-Reinforcement Learning with Causal Representation

TL;DR

CausalCOMRL introduces causal representation learning into offline meta-reinforcement learning to improve task generalization and reduce spurious correlations, leading to better policy performance across benchmarks.

Contribution

It is the first to integrate causal representations into context-based offline meta-RL, enhancing task generalization and robustness against confounders.

Findings

Outperforms existing methods on most meta-RL benchmarks.

Effectively uncovers causal relationships among task components.

Improves task representation distinction using mutual information and contrastive learning.

Abstract

Context-based offline meta-reinforcement learning (OMRL) methods have achieved appealing success by leveraging pre-collected offline datasets to develop task representations that guide policy learning. However, current context-based OMRL methods often introduce spurious correlations, where task components are incorrectly correlated due to confounders. These correlations can degrade policy performance when the confounders in the test task differ from those in the training task. To address this problem, we propose CausalCOMRL, a context-based OMRL method that integrates causal representation learning. This approach uncovers causal relationships among the task components and incorporates the causal relationships into task representations, enhancing the generalizability of RL agents. We further improve the distinction of task representations from different tasks by using mutual information optimization and contrastive learning. Utilizing these causal task representations, we employ SAC to optimize policies on meta-RL benchmarks. Experimental results show that CausalCOMRL achieves better performance than other methods on most benchmarks.