102 search results - page 5 / 21 » MDPs with Non-Deterministic Policies |
NIPS
2000
13 years 8 months ago
2000
We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and p...
ORL
2007
13 years 7 months ago
2007
The unichain condition requires that every policy in an MDP result in a single ergodic class, and guarantees that the optimal average cost is independent of the initial state. We ...
ATAL
2006
Springer
13 years 11 months ago
2006
Springer
In this paper we describe the initial results of an investigation into the relationship between Markov Decision Processes (MDPs) and Belief-Desire-Intention (BDI) architectures. W...
ICML
2010
IEEE
13 years 8 months ago
2010
IEEE
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
AAMAS
2010
Springer
13 years 7 months ago
2010
Springer
Abstract In this paper we address the problem of simultaneous learning and coordination in multiagent Markov decision problems (MMDPs) with infinite state-spaces. We separate this ...