SEAPoT-RL: Selective Exploration Algorithm for Policy Transfer in RL.
Akshay NarayanZhuoru LiTze-Yun LeongPublished in: AAAI (2017)
Keyphrases
- learning algorithm
- reinforcement learning
- model free
- computational complexity
- cost function
- dynamic programming
- detection algorithm
- optimal solution
- computational cost
- preprocessing
- optimization algorithm
- continuous domains
- probabilistic model
- transfer learning
- least squares
- function approximation
- optimal policy
- image restoration
- segmentation algorithm
- similarity measure