Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning
This addresses memory inefficiency in replay buffers for reinforcement learning agents, offering a practical improvement for resource-constrained applications.
The paper tackles catastrophic forgetting in deep reinforcement learning by introducing a map-based experience replay method that uses a self-organizing network to merge similar state transitions, reducing memory usage by up to 90% while maintaining performance within 5% of baseline methods.
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.