Stochastic Games with Lexicographic Reachability-Safety Objectives.
Krishnendu ChatterjeeJoost-Pieter KatoenMaximilian WeiningerTobias WinklerPublished in: CAV (2) (2020)
Keyphrases
- stochastic games
- nash equilibria
- multiagent reinforcement learning
- games with incomplete information
- markov decision processes
- multi agent
- state space
- learning automata
- nash equilibrium
- reinforcement learning algorithms
- average reward
- imperfect information
- incomplete information
- mathematical programming
- infinite horizon
- combinatorial optimization
- lower bound
- neural network