Online Markov Decision Processes

DOI10.1287/moor.1090.0396zbMath1218.90207MaRDI QIDQ3169063

Yishay Mansour, Eyal Even-Dar, Sham M. Kakade

Publication date: 27 April 2011

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/5e838b1d5a0dc3454dad082b2ca6b9bf301bd25c

zbMATH Keywords

Markov decision process; no-regret algorithms

Mathematics Subject Classification ID

68Q32: Computational learning theory

68T05: Learning and adaptive systems in artificial intelligence

90C40: Markov and semi-Markov decision processes

Related Items

Unnamed Item, Unnamed Item, Online Learning over a Finite Action Set with Limited Switching, Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization, An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions, Learning Stationary Nash Equilibrium Policies in \(n\)-Player Stochastic Games with Independent Chains, Online regret bounds for Markov decision processes with deterministic transitions, Online spatio-temporal matching in stochastic and dynamic domains, Approachability in Stackelberg stochastic games with vector costs, Bayesian adversarial multi-node bandit for optimal smart grid protection against cyber attacks, Multi-period orienteering with uncertain adoption likelihood and waiting at customers, Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes, Reinforcement Learning in Robust Markov Decision Processes, Chasing Ghosts: Competing with Stateful Policies