Unravel Structured Heterogeneity of Tasks in Meta-Reinforcement Learning via Exploratory Clustering
Lists
Only you see this
Abstract
Meta-reinforcement learning (meta-RL) is developed to quickly solve new tasks by leveraging knowledge from prior tasks. The assumption that tasks are drawn IID is typically made in previous studies, which ignore possible structured heterogeneity of tasks. The non-transferable knowledge caused by structured heterogeneity hinders fast adaptation in new tasks. In this paper, we formulate the structured heterogeneity of tasks via clustering such that transferable knowledge can be inferred within different clusters and non-transferable knowledge would be excluded across clusters thereby. To facilitate so, we develop a dedicated exploratory policy to discover task clusters by reducing uncertainty in posterior inference. Within the identified clusters, the exploitation policy is able to solve related tasks by utilizing knowledge shared within the clusters. Experiments on various MuJoCo tasks showed the proposed method can unravel cluster structures effectively in both rewards and state dynamics, proving strong advantages against a set of state-of-the-art baselines.
BibTeX
@inproceedings{chu2023unravel,
author = {Zhendong Chu and Hongning Wang},
title = {{Unravel Structured Heterogeneity of Tasks in Meta-Reinforcement Learning via Exploratory Clustering}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=Pe7R48fCkM_},
}