Asynchronous Decentralized Q-Learning in Stochastic Games.
Bora YongacogluGürdal ArslanSerdar YükselPublished in: CDC (2023)
Keyphrases
- stochastic games
- multi agent
- reinforcement learning algorithms
- multiagent reinforcement learning
- multi agent reinforcement learning
- state action
- single agent
- cooperative
- reinforcement learning
- learning agent
- markov decision processes
- rl algorithms
- state space
- model free
- average reward
- function approximation
- learning automata
- repeated games
- nash equilibria
- multi agent systems
- temporal difference
- autonomous agents
- learning algorithm
- sufficient conditions
- dynamic environments
- finite state
- planning problems