Recurrent Reinforcement Learning with Memoroids

arXiv:2402.09900v4 Announce Type: replace-cross Abstract: Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long sequences, especially compared to an emerging class of memory models called Linear Recurrent Models. We discover that the recurrent update of these models resembles a monoid, leading us to reformulate existing models using a novel monoid-based framework that we call memoroids. We revisit the traditional approach to batching in recurrent reinforcement learning, highlighting theoretical and empirical deficiencies. We leverage memoroids to propose a batching method that improves sample efficiency, increases the return, and simplifies the implementation of recurrent loss functions in reinforcement learning.

Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling
StateX: Enhancing RNN Recall via Post-training State Expansion
Residual Reservoir Memory Networks
Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes
Finite-Time Analysis of MCTS in Continuous POMDP Planning

Source: arXiv cs.AI | 2026-08-28

Related