AI & ML
Adaptive Memory for Online Reinforcement Learning under Sparse Model Changes
arXiv stat.ML0 views
arXiv:2611.21879v1 Announce Type: cross Abstract: We study the discounted reinforcement learning (RL) problem in a setting where the underlying environment changes between deployments. Each deployment provides $H$ observations from a fixed MDP. The reward function and transition kernel are fixed within each deployment. Across deployments, at most an $\epsilon >0$ fraction of the reward and transition kernel entries may change. In this setting, learning each model to deploy from scratch may discard useful observations from past deployments, whereas pooling all past observations can bias the estimates of entries that have already changed. We then propose an algorithm that for each state and action pair, selects how much history to reuse to estimate the reward and probabilities of the next state. We start with observations from the current deployment and add earlier deployment observations one at a time, the most recent first. After each addition, we check whether a single average reward agrees with the estimates from all histories considered until that point. We apply the same check to the distribution of next states. For each estimate, we leverage the last history that passes these aforementioned checks. The optimal control policy is then computed on top of the fitted MDP. We characterize the average gap between the optimal return and the return of the learner's policies over a finite number of deployments. We demonstrate that when $0< |S|\epsilon \leq 2$, with $|S|$ being the cardinality of the state space, our algorithm needs only the observations from the most recent $O(1/\epsilon)$ deployments, and achieves a long-run average gap of at most $\widetilde{O}(\sqrt{\epsilon/H})$.
Source:https://arxiv.org/abs/2611.21879PreviousBias-Reduced and Parallel Heavy-Tailed Stochastic Convex Optimization in $\ell_p$ GeometriesNextCancellation-Free Constrained SquareCB for Safe Controller Selection
Related posts
Introduction to CUDA Beyond the Syntax
0Hacker News New
Physics AI: The illusion of ground truth
0Hacker News New
RiddleBell Puzzle Alarm Clock
0Hacker News New
Open WebUI – Open Terminal: A Computer for Your AI Agents
0Hacker News New
LLMs abandon correct climate facts when users push back (UNESCO/UCL)
0Hacker News New
Standard Support: How AI agents ask for support
0Hacker News New