Newton-based Policy Search for Networked Multi-agent Reinforcement Learning.
Giorgio ManganiniSimone FioravantiGiorgia RamponiPublished in: CDC (2022)
Keyphrases
- multi agent reinforcement learning
- policy search
- reinforcement learning
- reinforcement learning algorithms
- learning agents
- multi agent
- stochastic games
- dynamic programming
- learning agent
- function approximation
- learning algorithm
- state space
- model free
- learning process
- reward function
- markov decision processes
- policy gradient
- optimal control
- transfer learning
- supervised learning
- distributed control