Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of stochastic approximation theory via a new convergence theorem. The theorem establishes a general class of convergent algorithms to which both TD(lambda) and Q-learning belong.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7205 |
| Date | 01 August 1993 |
| Creators | Jaakkola, Tommi, Jordan, Michael I., Singh, Satinder P. |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 15 p., 77605 bytes, 356324 bytes, application/octet-stream, application/pdf |
| Relation | AIM-1441, CBCL-084 |
Page generated in 0.0021 seconds