Asymmetric Actor Critic for Image-Based Robot Learning.
Lerrel PintoMarcin AndrychowiczPeter WelinderWojciech ZarembaPieter AbbeelPublished in: CoRR (2017)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- optimal control
- approximate dynamic programming
- temporal difference
- gradient method
- neuro fuzzy
- reinforcement learning algorithms
- policy iteration
- function approximation
- average reward
- linear program
- dynamical systems
- monte carlo
- adaptive filtering
- step size
- evaluation function
- recursive least squares
- linear programming
- multi agent