Finite-sample convergence rates for q-learning and indirect algorithms

Advances in Neural Information Processing Systems

Volumn , Issue , 1999, Pages 996-1002

  Kearns, Michael ^a   Singh, Satinder ^a  

^a AT AND T LABS RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ITERATIVE METHODS; OPTIMIZATION;

CONVERGENCE RATES; EXPLORATION POLICY; MODEL BASED APPROACH; PERFORMANCE GUARANTEES; QUANTITATIVE COMPARISON; RAPID CONVERGENCE; SAMPLE COMPLEXITY; STATIONARY DISTRIBUTION;

REINFORCEMENT LEARNING;

EID: 84899026236     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. Jaakkola, T., and Jordan., M. I., Singh, S. On the convergence of stochastic iterative dynamic programming algorithms. Neural Computation, 6(6), 1185-1201, 1994.
2. C. J. C. H. Watkins. Learning from Delayed Rewards. Ph.D. thesis, Cambridge University, 1989.
3. R. S. Sutton and A. G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.
4. S. Mahadevan. Enhancing Transfer in Reinforcement Learning by Building Stochastic Models of Robot Actions. In Machine Learning: Proceedings of the Ninth International Conference, 1992.