The Complexity of Synchronizing Markov Decision Processes.
Laurent DoyenThierry MassartMahsa ShirmohammadiPublished in: CoRR (2016)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- reinforcement learning
- transition matrices
- policy iteration
- dynamic programming
- decision theoretic planning
- finite horizon
- reachability analysis
- partially observable
- decision problems
- decision processes
- average reward
- model based reinforcement learning
- state and action spaces
- planning under uncertainty
- average cost
- computational complexity
- factored mdps
- reinforcement learning algorithms
- reward function
- risk sensitive
- action sets
- semi markov decision processes
- infinite horizon
- state abstraction
- real time dynamic programming
- interval estimation
- markov decision process
- multi agent