Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning

arXiv:2406.04815v1 Announce Type: new
Abstract: Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviours). Using context encoders based on contrastive learning to enhance the generalisability of Meta-RL agents is now widely studied but faces challenges such as the requirement for a large sample size, also referred to as the $\log$-$K$ curse. To improve RL generalisation to different tasks, we first introduce Skill-aware Mutual Information (SaMI), …

abstract agents arxiv challenges context cs.ai cs.lg cs.ro environmental features information meta optimisation reinforcement reinforcement learning skill skills struggle tasks type