Bias and variance approximation in value function estimates
From MaRDI portal
Recommendations
- Simulation‐based Uniform Value Function Estimates of Markov Decision Processes
- Learning the variance of the reward-to-go
- An analysis of temporal-difference learning with function approximation
- A probabilistic analysis of bias optimality in unichain Markov decision processes
- Approximate gradient methods in policy-space optimization of Markov reward processes
Cited in
(23)- An active-set strategy to solve Markov decision processes with good-deal risk measure
- Compromise policy for multi-stage stochastic linear programming: variance and bias reduction
- The optimal unbiased value estimator and its relation to LSTD, TD and MC
- Rank-1 transition uncertainties in constrained Markov decision processes
- Towards min max generalization in reinforcement learning
- Spectral and graph-theoretic bounds on steady-state-probability estimation performance for an ergodic Markov chain
- Distributionally robust chance-constrained Markov decision processes with random payoff
- Policy-based branch-and-bound for infinite-horizon multi-model Markov decision processes
- Non-parametric policy search with limited information loss
- Off-policy evaluation for tabular reinforcement learning with synthetic trajectories
- Reinforcement learning in robust Markov decision processes
- Robust MDPs with k-rectangular uncertainty
- Percentile optimization in multi-armed bandit problems
- Sequential decision-making under uncertainty: a robust MDPs review
- scientific article; zbMATH DE number 7306868 (Why is no real title available?)
- Constrained Markov decision processes with uncertain costs
- Stochastic control with distributionally robust constraints for cyber-physical systems vulnerable to attacks
- Divide-and-conquer offline policy evaluation for contextual bandits
- Distributionally robust optimization for sequential decision-making
- Deterministic policies based on maximum regrets in MDPs with imprecise rewards
- Value function approximation using multiple aggregation for multiattribute resource management
- Convex approximations of random constrained Markov decision processes
- Joint chance-constrained Markov decision processes
This page was built for publication: Bias and variance approximation in value function estimates
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3116079)
