Multi-Task Deep Reinforcement Learning for Continuous Action Control.
Zhaoyang YangKathryn E. MerrickHussein A. AbbassLianwen JinPublished in: IJCAI (2017)
Keyphrases
- multi task
- reinforcement learning
- multi task learning
- policy search
- continuous action
- learning tasks
- transfer learning
- learning problems
- continuous state
- optimal control
- function approximation
- state space
- multi class
- control system
- learning algorithm
- action space
- control policy
- model free
- action selection
- reinforcement learning algorithms
- partially observable
- feature selection
- optimal policy
- supervised learning
- neural network
- support vector machine
- partially observable markov decision processes