Concurrent Markov decision processes for robot team learning.
Justin GirardM. Reza EmamiPublished in: Eng. Appl. Artif. Intell. (2015)
Keyphrases
- markov decision processes
- reinforcement learning
- model based reinforcement learning
- partially observable
- learning algorithm
- finite state
- optimal policy
- dynamic programming
- autonomous robots
- stochastic games
- average cost
- reinforcement learning algorithms
- state space
- objective function
- model checking
- sufficient conditions
- least squares
- factored mdps
- reachability analysis
- search space