Material Detail
An Analysis of Reinforcement Learning with Function Approximation
This video was recorded at 25th International Conference on Machine Learning (ICML), Helsinki 2008. We address the problem of computing the optimal Q-function in Markov decision problems with infinite state-space. We analyze the convergence properties of several variations of Q-learning when combined with function approximation, extending the analysis of TD-learning in (Tsitsilis and Van Roy, 1996) to stochastic control settings. We identify conditions under which such approximate methods converge with probability 1. We conclude with a brief discussion on the general applicability of our results and compare them with several related works.
Quality
- User Rating
- Comments
- Learning Exercises
- Bookmark Collections
- Course ePortfolios
- Accessibility Info
More about this material
- Mobile Compatibility:
- Not specified at this time
- Language:
- English
- Cost Involved:
- No
- Source Code Available:
- No
- Accessibility Information Available:
- Unknown
- Creative Commons:
-
This work is licensed under a Attribution-NonCommercial-NoDerivs 3.0 United States
