Material Detail

An Analysis of Reinforcement Learning with Function Approximation

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

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.
hidden