A polynomial algorithm for decentralized Markov decision processes with temporal constraints.
Aurélie BeynierAbdel-Illah MouaddibPublished in: AAMAS (2005)
Keyphrases
- markov decision processes
- temporal constraints
- dynamic programming
- state space
- learning algorithm
- machine learning
- np hard
- computational complexity
- policy iteration
- average reward
- incremental algorithms
- special case
- search space
- integrity constraints
- temporal information
- convergence rate
- decision theoretic planning