Fully distributed actor-critic architecture for multitask deep reinforcement learning.
Sergio Valcarcel MacuaIan DaviesAleksi TukiainenEnrique Munoz de CotePublished in: Knowl. Eng. Rev. (2021)
Keyphrases
- actor critic
- fully distributed
- reinforcement learning
- multi task
- policy gradient
- temporal difference
- transfer learning
- learning problems
- optimal control
- approximate dynamic programming
- reinforcement learning algorithms
- cooperative
- neuro fuzzy
- function approximation
- loosely coupled
- gradient method
- learning tasks
- policy iteration
- multi class
- rl algorithms
- peer to peer
- multi agent systems
- overlay network
- model free
- average reward
- machine learning
- distributed search
- markov decision processes
- supervised learning
- dynamic programming
- learning algorithm
- key distribution
- temporal difference learning
- feature selection