Continuous-time stochastic games with time-bounded reachability.
Tomás BrázdilVojtech ForejtJan KrcálJan KretínskýAntonín KuceraPublished in: Inf. Comput. (2013)
Keyphrases
- stochastic games
- state space
- markov decision processes
- reinforcement learning algorithms
- games with incomplete information
- nash equilibria
- markov chain
- average reward
- multiagent reinforcement learning
- multi agent
- learning agent
- dynamical systems
- reinforcement learning
- nash equilibrium
- robust optimization
- imperfect information
- learning automata
- optimal control
- infinite horizon
- repeated games
- finite state
- single agent
- incomplete information
- game theory
- heuristic search