Average reward reinforcement learning: foundations, algorithms, and empirical results

Machine Learning

Volumn 22, Issue 1-3, 1996, Pages 159-195

  Mahadevan, Sridhar ^a  

^a University of South Florida   (United States)

Author keywords

Markov decision processes; Reinforcement learning

Indexed keywords

AUTOMATA THEORY; DYNAMIC PROGRAMMING; LEARNING ALGORITHMS; MARKOV PROCESSES; OPTIMAL CONTROL SYSTEMS; PERFORMANCE; SENSITIVITY ANALYSIS;

BIAS OPTIMAL; GAIN OPTIMAL; LEARNING AUTOMATA; MARKOV DECISION PROCESSES; REINFORCEMENT LEARNING;

LEARNING SYSTEMS;

EID: 0029752592     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1007/BF00114727     Document Type: Article

References (8)

1. Baird, L. Personal Communication.
2. Baird, L., (1995). Residual algorithms: Reinforcement learning with function approximation In Proceedings of the 12th International Conference on Machine Learning, pages 30-37. Murgan Kaufmann.
3. Barto, A., Bradtke, S. & Singh, S. (1995). Learning to act using real-time dynamic programming. Artificial Intelligence, 72(1):81-138.
4. Bertsekas, D., (1982) Distributed dynamic programming. IEEE Transactions art Automatic Control, AC-27(3).
5. Bertsekas, D., (1987). Dynamic Programming: Deterministic and Stochastic Models. Prentice-Hall.
6. Blackwell, D., (1962) Discrete dynamic programming. Annals of Mathematical Statistics, 33:719-726.
7. Boutilier, C. & Puterman, M., (1905) Process-oriented planning and average-reward optimality. In Proceedings of the Fourteenth JCAI, pages 1096-1103. Morgan Kaufmann.
8. Dayan, P. & Hinton, G., (1992) Feudal reinforcement learning. In Neural Information Processing Systems (NIPS), pages 271-278.