An emphatic approach to the problem of off-policy temporal-difference learning

zbMATH Open1360.68712arXiv1503.04269MaRDI QIDQ2810885FDOQ2810885

Authors: Richard S. Sutton, A. Rupam Mahmood, Martha White 

Publication date: 6 June 2016

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1503.04269

Recommendations

• On Generalized Bellman Equations and Temporal-Difference Learning
• On Generalized Bellman Equations and Temporal-Difference Learning
• Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize
• \(\text{Q}(\lambda)\) with off-policy corrections
• A finite time analysis of temporal difference learning with linear function approximation

zbMATH Keywords

convergencestabilityfunction approximationoff-policy learningtemporal-difference learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (12)

• Distributed consensus-based multi-agent temporal-difference learning
• Gradient temporal-difference learning for off-policy evaluation using emphatic weightings
• Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning
• Policy evaluation with temporal differences: a survey and comparison
• On Generalized Bellman Equations and Temporal-Difference Learning
• Online Bootstrap Inference For Policy Evaluation In Reinforcement Learning
• Adaptive importance sampling for value function approximation in off-policy reinforcement learning
• Off-policy temporal difference learning with distribution adaptation in fast mixing chains
• Statistical inference for online decision making via stochastic gradient descent
• Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• \(\text{Q}(\lambda)\) with off-policy corrections

This page was built for publication: An emphatic approach to the problem of off-policy temporal-difference learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2810885)