Control with Distributed Deep Reinforcement Learning: Learn a Better Policy.
Qihao LiuXiaofeng LiuGuoping CaiPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- control policy
- optimal policy
- function approximators
- action selection
- control problems
- multi agent
- optimal control
- control policies
- master slave
- policy search
- approximate dynamic programming
- reward signal
- robot control
- blackboard architecture
- distributed control
- partially observable environments
- agent receives
- function approximation
- control strategies
- distributed systems
- peer to peer
- machine learning
- cooperative
- control system
- actor critic
- control method
- control strategy
- learning algorithm
- learning process
- markov decision processes
- markov decision process
- long run
- infinite horizon
- complex domains
- reward function
- temporal difference