AI & ML
Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise
arXiv stat.ML0 views
arXiv:2411.13711v2 Announce Type: replace-cross Abstract: This paper establishes, to our knowledge, the first almost sure convergence rate and the first maximal concentration bound with sub-Weibull tails for general contractive stochastic approximation algorithms with Markovian noise. As a corollary, we also obtain convergence rates in $L^p$. Key to our successes is a novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing (instead of constant) length. Applications yield the first almost sure convergence rate for $Q$-learning without count-based learning rates and the first maximal concentration bound for off-policy temporal difference learning, both with Markovian samples.
Source:https://arxiv.org/abs/2411.13711PreviousDesigning Algorithmic Recommendations to Achieve Human-AI ComplementarityNexttempdisagg: A Python Framework for Temporal Disaggregation of Time Series Data
Related posts
How we find viral moments in a 6-hour stream in 4 minutes
0dev.to
One red light, four stalls
0dev.to
Testing Political Alignment in Chinese AI Models: What Developers Need to Know
0dev.to
LLM Inference Optimization Interview Questions and Answers
0dev.to
How to Close a Deal That Keeps Stalling: A Mutual Action Plan Template and Closing Techniques for Founder-Led Sales
0dev.to

Roast My Dev Desktop: Zero Minimalism, Maximum Chaos
0dev.to