Decentralized Model-Free Reinforcement Learning in Stochastic Games with Average-Reward Objective.
Romain CravicNicolas GastBruno GaujalPublished in: AAMAS (2023)
Keyphrases
- stochastic games
- average reward
- policy gradient
- markov decision processes
- optimal policy
- long run
- reinforcement learning
- multi agent
- model free
- state action
- nash equilibria
- policy iteration
- repeated games
- infinite horizon
- cooperative
- reinforcement learning algorithms
- machine learning
- markov chain
- learning automata
- state space
- knowledge base