Balancing Exploration and Exploitation in Self-imitation Learning.
Chun-Yao KangMing-Syan ChenPublished in: PAKDD (2) (2020)
Keyphrases
- imitation learning
- balancing exploration and exploitation
- reinforcement learning
- learning to rank
- reinforcement learning algorithms
- state space
- reinforcement learning methods
- learning algorithm
- model free
- markov decision processes
- control problems
- machine learning
- robotic systems
- data sets
- humanoid robot
- maximum margin
- pairwise
- relational databases
- information extraction
- transfer learning