Multi-Agent Natural Actor-Critic Reinforcement Learning Algorithms.
Prashant TrivediNandyala HemachandraPublished in: Dyn. Games Appl. (2023)
Keyphrases
- natural actor critic
- reinforcement learning algorithms
- reinforcement learning problems
- reinforcement learning
- multi agent
- reinforcement learning methods
- model free
- function approximation
- state space
- actor critic
- markov decision processes
- temporal difference
- learning algorithm
- multi agent systems
- policy iteration
- stochastic games
- control problems
- optimal policy
- supervised learning
- single agent
- function approximators
- multiple agents
- markov decision problems
- robot arm
- neural network
- transfer learning
- support vector machine svm
- linear programming
- dynamic programming
- machine learning