Imitation-Projected Programmatic Reinforcement Learning.
Abhinav VermaHoang Minh LeYisong YueSwarat ChaudhuriPublished in: NeurIPS (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- control problems
- model free
- structured light
- optimal policy
- learning algorithm
- temporal difference
- machine learning
- optimal control
- markov decision processes
- supervised learning
- temporal difference learning
- reinforcement learning algorithms
- database
- dynamic programming
- learning process
- direct policy search
- learning problems
- imitation learning
- relational reinforcement learning
- robotic control
- learned knowledge
- robot control
- evolutionary algorithm
- decision making
- data mining
- real time