Material Detail
Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs
This video was recorded at 26th International Conference on Machine Learning (ICML), Montreal 2009. In this paper we propose an algorithm for polynomial-time reinforcement learning in factored Markov decision processes (FMDPs). The factored optimistic initial model (FOIM) algorithm, maintains an empirical model of the FMDP in a conventional way, and always follows a greedy policy with respect to its model. The only trick of the algorithm is that the model is initialized optimistically. We prove that with suitable initialization (i) FOIM converges to the fixed point of approximate value iteration (AVI); (ii) the number of steps when the agent makes non-near-optimal decisions (with respect to the solution of AVI) is polynomial in all relevant quantities; (iii) the per-step costs of the algorithm are also polynomial. To our best knowledge, FOIM is the first algorithm with these properties.
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
