Cooperative Multi-agent Policy Gradient.
Guillaume BonoJilles Steeve DibangoyeLaëtitia MatignonFlorian PereyronOlivier SimoninPublished in: ECML/PKDD (1) (2018)
Keyphrases
- cooperative multi agent
- policy gradient
- reinforcement learning
- actor critic
- function approximation
- parametric optimization
- reinforcement learning algorithms
- gradient method
- logic programming
- optimal control
- model free reinforcement learning
- approximation methods
- reinforcement learning methods
- state space
- markov decision processes
- average reward
- single agent
- state action
- optimal policy
- learning algorithm
- temporal difference
- natural language
- control system