ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning

Excerpt

arXiv:2610.00592v1 Announce Type: new Abstract: In partially observable reinforcement learning (RL), a later observation can make stored information obsolete or change what it implies for the next decision. Memory architectures and benchmarks for RL mostly test retention, the ability to keep information unchanged until it is needed. We formalize two further requirements. Rewriting sets the decision-relevant content to a value independent of the old one, and experience fusion transforms the old c