AI RESEARCH
AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning
arXiv CS.LG
•
ArXi:2410.04498v2 Announce Type: replace In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply and reuse high-value policies, lacking a deeper refining and filtering of diverse past experiences and hence limiting the capability of memory. In this paper, we propose AdaMemento, an adaptive memory-enhanced RL framework.