Structured Control Nets for Deep Reinforcement Learning.
Mario SroujiJian ZhangRuslan SalakhutdinovPublished in: ICML (2018)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- robot control
- function approximation
- control policy
- learning algorithm
- multi agent
- structured data
- control system
- control theory
- control method
- multi agent reinforcement learning
- machine learning
- learning problems
- markov decision processes
- optimal policy
- probabilistic model