Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning.
Yuchen XiaoXueguang LyuChristopher AmatoPublished in: MRS (2021)
Keyphrases
- reinforcement learning
- actor critic
- multi agent
- reinforcement learning algorithms
- function approximation
- temporal difference
- policy gradient
- optimal control
- state space
- approximate dynamic programming
- machine learning
- learning problems
- gradient method
- policy iteration
- model free
- transfer learning
- optimal policy
- dynamic programming
- multi agent systems
- fuzzy logic
- partially observable
- reinforcement learning methods
- temporal difference learning
- learning algorithm
- rl algorithms
- natural actor critic
- average reward
- partially observable markov decision processes
- single agent
- multiple agents
- neuro fuzzy
- markov decision processes
- machine learning algorithms
- supervised learning