Playing Against Fair Adversaries in Stochastic Games with Total Rewards.
Pablo F. CastroPedro R. D'ArgenioRamiro DemasiLuciano PutruelePublished in: CAV (2) (2022)
Keyphrases
- stochastic games
- markov decision processes
- imperfect information
- nash equilibria
- reinforcement learning
- reinforcement learning algorithms
- multiagent reinforcement learning
- multi agent
- average reward
- repeated games
- nash equilibrium
- infinite horizon
- learning automata
- reward function
- game playing
- state space
- robust optimization
- partially observable
- decision making
- cooperative
- policy iteration
- single agent
- finite state
- optimal policy
- expert systems
- np hard
- game theoretic
- game theory
- mobile robot