Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning

About

We study offline meta-reinforcement learning, a practical reinforcement learning paradigm that learns from offline data to adapt to new tasks. The distribution of offline data is determined jointly by the behavior policy and the task. Existing offline meta-reinforcement learning algorithms cannot distinguish these factors, making task representations unstable to the change of behavior policies. To address this problem, we propose a contrastive learning framework for task representations that are robust to the distribution mismatch of behavior policies in training and test. We design a bi-level encoder structure, use mutual information maximization to formalize task representation learning, derive a contrastive learning objective, and introduce several approaches to approximate the true distribution of negative pairs. Experiments on a variety of offline meta-reinforcement learning benchmarks demonstrate the advantages of our method over prior methods, especially on the generalization to out-of-distribution behavior policies. The code is available at https://github.com/PKU-AI-Edge/CORRO.

Haoqi Yuan, Zongqing Lu• 2022

Related benchmarks

TaskDatasetResultRank
Meta-Reinforcement LearningHopper-Param (ID)
Average Return302
30
Meta-Reinforcement LearningCheetah-Vel-Sparse (OOD)
Average Return260
15
Meta-Reinforcement LearningCheetah-Vel
Average Return60
10
Meta-Reinforcement LearningWalker-Param (ID)
Average Return119
10
Offline Meta-Reinforcement LearningPoint-Robot sampled 10 unseen (test)
Average Return-7.8
10
Meta-Reinforcement LearningWalker-Param
Average Return127
10
Meta-Reinforcement LearningPoint-Robot Sparse
Average Return38
10
Meta-Reinforcement LearningWalker Param-Sparse
Average Return78
10
Offline Meta-Reinforcement LearningWalker-Rand-Params sampled 10 unseen (test)
Average Return312.5
10
Meta-Reinforcement LearningCheetah-Vel ID
Average Return214
10
Showing 10 of 22 rows

Other info

Follow for update