Learning to Collaborate in Markov Decision Processes.
Goran RadanovicRati DevidzeDavid C. ParkesAdish SinglaPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- reinforcement learning
- partially observable
- finite state
- model based reinforcement learning
- optimal policy
- state abstraction
- policy iteration
- stochastic games
- learning algorithm
- reachability analysis
- state space
- supervised learning
- average reward
- planning under uncertainty
- decision theoretic planning