@article{Fu_Tang_Hao_Chen_Feng_Li_Liu_2021, title={Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/16914}, DOI={10.1609/aaai.v35i8.16914}, abstractNote={Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a few adaptation steps. We argue that improving the quality of context involves answering two questions: 1. How to train a compact and sufficient encoder that can embed the task-specific information contained in prior trajectories? 2. How to collect informative trajectories of which the corresponding context reflects the specification of tasks? To this end, we propose a novel Meta-RL framework called CCM (Contrastive learning augmented Context-based Meta-RL). We first focus on the contrastive nature behind different tasks and leverage it to train a compact and sufficient context encoder. Further, we train a separate exploration policy and theoretically derive a new information-gain-based objective which aims to collect informative trajectories in a few steps. Empirically, we evaluate our approaches on common benchmarks as well as several complex sparse-reward environments. The experimental results show that CCM outperforms state-of-the-art algorithms by addressing previously mentioned problems respectively.}, number={8}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Fu, Haotian and Tang, Hongyao and Hao, Jianye and Chen, Chen and Feng, Xidong and Li, Dong and Liu, Wulong}, year={2021}, month={May}, pages={7457-7465} }