A Theoretical and Empirical Analysis of Reward Transformations in Multi-Objective Stochastic Games.
Patrick MannionJim DugganEnda HowleyPublished in: AAMAS (2017)
Keyphrases
- stochastic games
- multi objective
- average reward
- markov decision processes
- evolutionary algorithm
- state action
- optimal policy
- long run
- reinforcement learning
- learning agent
- multiagent reinforcement learning
- genetic algorithm
- nash equilibria
- reward function
- learning automata
- multi agent
- objective function
- policy iteration
- markov chain
- nash equilibrium
- reinforcement learning algorithms
- model free
- optimization problems
- imperfect information
- cooperative
- finite state
- infinite horizon
- state space
- incomplete information