Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening.
Frank S. HeYang LiuAlexander G. SchwingJian PengPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning problems
- deep architectures
- learning capabilities
- online learning
- deep learning
- inductive inference
- active learning
- knowledge acquisition
- learning tasks
- reinforcement learning methods
- temporal difference learning
- average reward reinforcement learning
- learning environment
- actor critic
- autonomous learning
- robot control
- model free
- function approximation
- neural network
- transfer learning
- background knowledge
- supervised learning
- multi agent