Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
arxiv(2024)
摘要
Exploration efficiency poses a significant challenge in goal-conditioned
reinforcement learning (GCRL) tasks, particularly those with long horizons and
sparse rewards. A primary limitation to exploration efficiency is the agent's
inability to leverage environmental structural patterns. In this study, we
introduce a novel framework, GEASD, designed to capture these patterns through
an adaptive skill distribution during the learning process. This distribution
optimizes the local entropy of achieved goals within a contextual horizon,
enhancing goal-spreading behaviors and facilitating deep exploration in states
containing familiar structural patterns. Our experiments reveal marked
improvements in exploration efficiency using the adaptive skill distribution
compared to a uniform skill distribution. Additionally, the learned skill
distribution demonstrates robust generalization capabilities, achieving
substantial exploration progress in unseen tasks containing similar local
structures.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要