A3C-GS: Adaptive Moment Gradient Sharing With Locks for Asynchronous Actor-Critic Agents.
Alfonso B. LabaoMygel Andrei MartijaProspero C. NavalPublished in: IEEE Trans. Neural Networks Learn. Syst. (2021)
Keyphrases
- actor critic
- policy gradient
- gradient method
- single agent
- multi agent systems
- reinforcement learning
- multi agent
- multiple agents
- temporal difference
- cooperative
- dynamic environments
- neuro fuzzy
- function approximation
- optimal control
- approximate dynamic programming
- recursive least squares
- machine learning
- decision making
- reinforcement learning methods
- reinforcement learning algorithms
- neural network
- approximation methods
- learning agent
- fuzzy sets
- learning capabilities