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

arXiv: https://arxiv.org/abs/2502.00983 · HTML: https://mlsanity.com/paper/2502.00983/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 8 of its 64 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Placed in

- Offline RL and imitation learning from data / [Decision transformers and sequence modeling](https://mlsanity.com/offlinerl/decision-transformers-and-sequence-modeling/)

## Builds on (most cited first, 8 of 8)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [A Tutorial on Meta-Reinforcement Learning](https://mlsanity.com/paper/2301.08028/) (2023)
- [Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning](https://mlsanity.com/paper/2402.02429/) (2024)
- [Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning](https://mlsanity.com/paper/2102.10774/) (2021)

## Built on by (most cited first, 3 of 3)

- [LLaPipe: LLM-Guided Reinforcement Learning for Automated Data Preparation Pipeline Construction](https://mlsanity.com/paper/2507.13712/) (2025)
- [SoftPipe: A Soft-Guided Reinforcement Learning Framework for Automated Data Preparation](https://mlsanity.com/paper/2507.13710/) (2025)
- [Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning](https://mlsanity.com/paper/2610.15428/) (2026)

## Abstract (arXiv)

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.