Reinforcement Learning with Fast and Forgetful Memory
This addresses the need for efficient memory models in RL for real-world tasks, though it is incremental as it builds on existing recurrent RL algorithms.
The paper tackles the problem of memory in partially observable reinforcement learning by introducing Fast and Forgetful Memory, a model designed specifically for RL that achieves greater reward and trains two orders of magnitude faster than recurrent neural networks across various benchmarks.
Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed from Supervised Learning (SL), even though RL tends to exhibit different training and efficiency characteristics. Addressing this discrepancy, we introduce Fast and Forgetful Memory, an algorithm-agnostic memory model designed specifically for RL. Our approach constrains the model search space via strong structural priors inspired by computational psychology. It is a drop-in replacement for recurrent neural networks (RNNs) in recurrent RL algorithms, achieving greater reward than RNNs across various recurrent benchmarks and algorithms without changing any hyperparameters. Moreover, Fast and Forgetful Memory exhibits training speeds two orders of magnitude faster than RNNs, attributed to its logarithmic time and linear space complexity. Our implementation is available at https://github.com/proroklab/ffm.