Continuous-Time Stochastic Games with Time-Bounded Reachability.
Tomás BrázdilVojtech ForejtJan KrcálJan KretínskýAntonín KuceraPublished in: FSTTCS (2009)
Keyphrases
- stochastic games
- state space
- markov decision processes
- reinforcement learning algorithms
- nash equilibria
- games with incomplete information
- markov chain
- learning automata
- average reward
- multiagent reinforcement learning
- multi agent
- repeated games
- dynamical systems
- nash equilibrium
- optimal control
- robust optimization
- reinforcement learning
- infinite horizon
- learning agent
- heuristic search
- finite state
- incomplete information
- imperfect information
- mathematical programming
- policy iteration
- knowledge acquisition
- linear programming
- dynamic programming
- machine learning