Sciweavers

771 search results - page 1 / 155
» Markov Decision Processes with Arbitrary Reward Processes
Sort
View
EWRL
2008
13 years 6 months ago
Markov Decision Processes with Arbitrary Reward Processes
Abstract. We consider a control problem where the decision maker interacts with a standard Markov decision process with the exception that the reward functions vary arbitrarily ove...
Jia Yuan Yu, Shie Mannor, Nahum Shimkin
CDC
2009
IEEE
133views Control Systems» more  CDC 2009»
13 years 9 months ago
Arbitrarily modulated Markov decision processes
— We consider decision-making problems in Markov decision processes where both the rewards and the transition probabilities vary in an arbitrary (e.g., nonstationary) fashion. We...
Jia Yuan Yu, Shie Mannor
ALT
2006
Springer
14 years 1 months ago
Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence
We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions. The task for an age...
Daniil Ryabko, Marcus Hutter
AAAI
1997
13 years 5 months ago
Incremental Methods for Computing Bounds in Partially Observable Markov Decision Processes
Partially observable Markov decision processes (POMDPs) allow one to model complex dynamic decision or control problems that include both action outcome uncertainty and imperfect ...
Milos Hauskrecht
ICML
2006
IEEE
14 years 5 months ago
Probabilistic inference for solving discrete and continuous state Markov Decision Processes
Inference in Markov Decision Processes has recently received interest as a means to infer goals of an observed action, policy recognition, and also as a tool to compute policies. ...
Marc Toussaint, Amos J. Storkey