Expected Lenient Q-learning: a fast variant of the Lenient Q-learning algorithm for cooperative stochastic Markov games.
Elmehdi AmhraouiTawfik MasrourPublished in: Int. J. Mach. Learn. Cybern. (2024)
Keyphrases
- markov games
- cooperative
- reinforcement learning algorithms
- multiagent reinforcement learning
- learning algorithm
- reinforcement learning
- markov decision processes
- model free
- multiagent systems
- multi agent
- state space
- stochastic games
- function approximation
- stochastic approximation
- control problems
- learning rate
- temporal difference learning
- temporal difference
- nash equilibrium
- game theory
- machine learning algorithms
- reward function
- learning agent
- monte carlo
- learning automata
- markov decision process
- machine learning