AUTHOR=Hafez Muhammad Burhan , Immisch Tilman , Weber Tom , Wermter Stefan 

TITLE=Map-based experience replay: a memory-efficient solution to catastrophic forgetting in reinforcement learning

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2023.1127642

DOI=10.3389/fnbot.2023.1127642

ISSN=1662-5218

ABSTRACT=Deep Reinforcement Learning agents often suffer from catastrophic forgetting, forgetting previously found solutions in parts of the input space when training on new data. Replay Memories are a common solution to the problem, decorrelating and shuffling old and new training samples. They naively store state transitions as they come in, without regard for redundancy. We introduce a novel cognitive-inspired replay memory approach based on the Grow-When-Required (GWR) self-organizing network, which resembles a map-based mental model of the world. Our approach organizes stored transitions into a concise environment-model-like network of state-nodes and transition-edges, merging similar samples to reduce the memory size and increase pair-wise distance among samples, which increases the relevancy of each sample. Overall, our paper shows that map-based experience replay allows for significant memory reduction with only small performance decreases.