Some Asymptotic Results in Discounted Repeated Games of One-Sided Incomplete Information.
Martin W. CrippsJonathan P. ThomasPublished in: Math. Oper. Res. (2003)
Keyphrases
- repeated games
- incomplete information
- query answering
- average reward
- autonomous agents
- markov decision processes
- infinite horizon
- partial information
- missing information
- optimal policy
- first order logic
- dynamic programming
- worst case
- finite horizon
- stochastic games
- expert systems
- knowledge representation
- machine learning
- long run
- uncertain information