Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation.
Xin WangWenhan XiongHongmin WangWilliam Yang WangPublished in: ECCV (16) (2018)
Keyphrases
- model free
- model based reinforcement learning
- reinforcement learning
- markov decision processes
- function approximation
- policy iteration
- reinforcement learning algorithms
- temporal difference
- decision trees
- transfer learning
- background knowledge
- optimal policy
- linear programming
- supervised learning
- state space
- training data
- neural network