An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions

DOI10.1162/NECO_A_00808zbMATH Open1472.68149DBLPjournals/neco/MaZHS16OpenAlexW2225522132WikidataQ47600318 ScholiaQ47600318MaRDI QIDQ5380403FDOQ5380403

Kohei Hatano, Yao Ma, Tingting Zhao, Masashi Sugiyama

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_00808

Recommendations

• Online learning in Markov decision processes with continuous actions
• Potential-Based Online Policy Iteration Algorithms for Markov Decision Processes
• Policy Gradient for Continuing Tasks in Discounted Markov Decision Processes
• A basic formula for online policy gradient algorithms
• An online actor-critic algorithm with function approximation for constrained Markov decision processes
• Policy gradient in continuous time
• Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes
• Gradient based policy optimization of constrained Markov decision processes

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27) Markov and semi-Markov decision processes (90C40)

Cites Work

• Online convex optimization in the bandit setting: gradient descent without a gradient
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Efficient algorithms for online decision problems
• Logarithmic Regret Algorithms for Online Convex Optimization
• Title not available (Why is that?)
• Markov Decision Processes with Arbitrary Reward Processes
• Online Markov Decision Processes
• Online Markov Decision Processes Under Bandit Feedback
• An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions

Cited In (2)

• Online Bootstrap Inference For Policy Evaluation In Reinforcement Learning
• An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions

This page was built for publication: An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380403)