Averaged-A3C for Asynchronous Deep Reinforcement Learning.
Song ChenXiaofang ZhangJin-Jin WuDi LiuPublished in: ICONIP (3) (2018)
Keyphrases
- reinforcement learning
- function approximation
- state space
- machine learning
- model free
- dynamic programming
- temporal difference
- markov decision processes
- robotic control
- relational reinforcement learning
- reinforcement learning algorithms
- action selection
- neural network
- evolutionary algorithm
- online discussion
- genetic algorithm
- decision making
- control problems
- learning agent
- learning agents
- autonomous learning
- asynchronous communication
- transition model
- state machines
- learning process
- decision trees