Bidding Games on Markov Decision Processes.
Guy AvniThomas A. HenzingerRasmus Ibsen-JensenPetr NovotnýPublished in: RP (2019)
Keyphrases
- markov decision processes
- action sets
- stochastic games
- state space
- reinforcement learning
- optimal policy
- finite state
- policy iteration
- dynamic programming
- finite horizon
- decision theoretic planning
- reinforcement learning algorithms
- reachability analysis
- average reward
- planning under uncertainty
- decision processes
- game theory
- infinite horizon
- transition matrices
- model based reinforcement learning
- nash equilibria
- factored mdps
- partially observable
- state and action spaces
- risk sensitive
- nash equilibrium
- markov decision process
- state abstraction
- data mining
- average cost
- real time dynamic programming
- model checking
- action space
- expected reward
- search space
- discounted reward
- semi markov decision processes