Parallel Algorithms for Solving Markov Decision Process.
Qi ZhangGuangzhong SunYinlong XuPublished in: ICA3PP (2009)
Keyphrases
- parallel algorithm
- markov decision process
- transition matrices
- state space
- markov decision processes
- optimal policy
- reinforcement learning
- infinite horizon
- parallel computation
- parallel programming
- finite horizon
- cluster of workstations
- initial state
- shared memory
- parallel version
- parallel implementations
- markov decision problems
- policy iteration
- search algorithm