Simulation-based optimization of Markov reward processes
From MaRDI portal
Publication:4540300
DOI10.1109/9.905687zbMath0992.93088OpenAlexW2120465407MaRDI QIDQ4540300
Peter Marbach, John N. Tsitsiklis
Publication date: 21 July 2002
Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/9.905687
Estimation and detection in stochastic control theory (93E10) Markov and semi-Markov decision processes (90C40)
Related Items (35)
A time aggregation approach to Markov decision processes ⋮ On the Fisher metric of conditional probability polytopes ⋮ Queueing Network Controls via Deep Reinforcement Learning ⋮ Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ Deep reinforcement trading with predictable returns ⋮ A reinforcement learning adaptive fuzzy controller for robots. ⋮ Geometry and convergence of natural policy gradient methods ⋮ Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning ⋮ Finding optimal memoryless policies of POMDPs under the expected average reward criterion ⋮ Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains ⋮ An online actor-critic algorithm with function approximation for constrained Markov decision processes ⋮ Performance optimization of queueing systems with perturbation realization ⋮ A tutorial on event-based optimization -- a new optimization framework ⋮ Event-based optimization of admission control in open queueing networks ⋮ Efficient Multi-objective Reinforcement Learning via Multiple-gradient Descent with Iteratively Discovered Weight-Vector Sets ⋮ Parameterized Markov decision process and its application to service rate control ⋮ Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme ⋮ Variance minimization of parameterized Markov decision processes ⋮ Smoothed functional-based gradient algorithms for off-policy reinforcement learning: a non-asymptotic viewpoint ⋮ On tight bounds for function approximation error in risk-sensitive reinforcement learning ⋮ Policy Gradient Approach of Event‐Based Optimization and Its Online Implementation ⋮ A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases ⋮ Basic ideas for event-based optimization of Markov systems ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ A sensitivity formula for risk-sensitive cost and the actor-critic algorithm ⋮ On-line policy gradient estimation with multi-step sampling ⋮ Dynamic programming and suboptimal control: a survey from ADP to MPC ⋮ Coupling based estimation approaches for the average reward performance potential in Markov chains ⋮ Deep reinforcement learning for inventory control: a roadmap ⋮ Natural actor-critic algorithms ⋮ Performance optimization for a class of generalized stochastic Petri nets ⋮ Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities ⋮ Concentration of Contractive Stochastic Approximation and Reinforcement Learning ⋮ Actor-Critic Algorithms with Online Feature Adaptation ⋮ Whittle index based Q-learning for restless bandits with average reward
This page was built for publication: Simulation-based optimization of Markov reward processes
