Stochastic optimization of controlled partially observable Markov decision processes

Proceedings of the IEEE Conference on Decision and Control

Volumn 1, Issue , 2000, Pages 124-129

  Bartlett, P L ^a   Baxter, J ^a  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; DYNAMIC PROGRAMMING; MARKOV PROCESSES; ONLINE SYSTEMS; OPTIMIZATION; PROBLEM SOLVING; STOCHASTIC CONTROL SYSTEMS;

PARTIALLY OBSERVABLE MARKOV DECISION PROCESS; STOCHASTIC OPTIMIZATION;

DECISION THEORY;

EID: 0034439308     PISSN: 07431546     EISSN: 25762370     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (27)

1. Stochastic optimaization
2. Estimation and approximation bounds for gradient-based reinforcement learning
3. Infinite-horizon gradient-based policy search
4. Learning to play chess using temporal-differences
5. Perturbation realization, potentials, and sensitivity analysis of Markov processes
6. Algorithms for sensitivity analysis of Markov chains through potentials and perturbation realization
7. Smooth perturbation derivative estimation for Markov chains
8. Stochastic approximation for Monte-Carlo optimization
9. Likelihood ratio gradient estimation for stochastic systems
10. Likelihood ratio gradient estimation for regenerative stochastic recursions
11. Reinforcement learning in POMDPs with function approximation
12. Simulation-based optimization of Markov reward processes
13. Sensitivity analysis via likelihood ratios
14. Sensitivity analysis for simulations via likelihood ratios
15. Some studies in machine learning using the game of checkers
16. Reinforcement learning for dynamic channel allocation in cellular telephone systems
17. Learning without state-estimation in partially observable Markovian decision processes
18. Practical issues in temporal difference learning
19. TD-Gammon, a self-teaching backgammon program, achieves master-level play
20. An analysis of temporal difference learning with function approximation
21. Simple statistical gradient-following algorithms for connectionist reinforcement learning
22. A reinforcement learning approach to job-shop scheduling