Bias and Variance Approximation in Value Function Estimates

DOI10.1287/mnsc.1060.0614zbMath1232.90344OpenAlexW2108692343MaRDI QIDQ3116079

Peng Sun, Shie Mannor, Duncan Simester, John N. Tsitsiklis

Publication date: 21 February 2012

Published in: Management Science (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/058bd34922c4fd5526fa28231b0a9ca2016a5c5b

zbMATH Keywords

confidence intervalvalue functionvariance bias

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (15)

Deterministic policies based on maximum regrets in MDPs with imprecise rewards ⋮ Constrained Markov decision processes with uncertain costs ⋮ The optimal unbiased value estimator and its relation to LSTD, TD and MC ⋮ Joint chance-constrained Markov decision processes ⋮ Compromise policy for multi-stage stochastic linear programming: variance and bias reduction ⋮ Off-policy evaluation for tabular reinforcement learning with synthetic trajectories ⋮ Spectral and graph-theoretic bounds on steady-state-probability estimation performance for an ergodic Markov chain ⋮ Towards Min Max Generalization in Reinforcement Learning ⋮ Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes ⋮ Reinforcement Learning in Robust Markov Decision Processes ⋮ Robust MDPs with k-Rectangular Uncertainty ⋮ Distributionally robust optimization for sequential decision-making ⋮ Unnamed Item ⋮ An active-set strategy to solve Markov decision processes with good-deal risk measure ⋮ Unnamed Item

This page was built for publication: Bias and Variance Approximation in Value Function Estimates