Memory-efficient Reinforcement Learning with Knowledge Consolidation. (arXiv:2205.10868v2 [cs.LG] UPDATED)

Artificial neural networks are promising for general function approximation
but challenging to train on non-independent or non-identically distributed data
due to catastrophic forgetting. The experience replay buffer, a standard
component in deep reinforcement learning, is often used to reduce forgetting
and improve sample efficiency by storing experiences in a large buffer and
using them for training later. However, a large replay buffer results in a
heavy memory burden, especially for onboard and edge devices with limited
memory capacities. We propose …

arxiv consolidation knowledge memory reinforcement reinforcement learning