MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components

Min Wang, Xin Li*, Leiji Zhang, Mingzhong Wang

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Meta-Reinforcement Learning (Meta-RL) aims to reveal shared characteristics in dynamics and reward functions across diverse training tasks. This objective is achieved by meta-learning a policy that is conditioned on task representations with encoded trajectory data or context, thus allowing rapid adaptation to new tasks from a known task distribution. However, since the trajectory data generated by the policy may be biased, the task inference module tends to form spurious correlations between trajectory data and specific tasks, thereby leading to poor adaptation to new tasks. To address this issue, we propose the Meta-RL with task unCertAinty feedback through decoupled context-aware Reward and Dynamics components (MetaCARD). MetaCARD distinctly decouples the dynamics and rewards when inferring tasks and learning the policy, and integrates task uncertainty feedback from policy evaluation into the task inference module. This design effectively reduces uncertainty in tasks with changes in dynamics or/and reward functions, thereby enabling accurate task identification and adaptation. The experiment results on both Meta-World and classical MuJoCo benchmarks show that MetaCARD significantly outperforms prevailing Meta-RL baselines, demonstrating its remarkable adaptation ability in sophisticated environments that involve changes in both reward functions and dynamics.

Original languageEnglish
Pages (from-to)15555-15562
Number of pages8
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume38
Issue number14
DOIs
Publication statusPublished - 25 Mar 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024

Fingerprint

Dive into the research topics of 'MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components'. Together they form a unique fingerprint.

Cite this