IQ-Learn: Inverse soft-Q Learning for Imitation.
Divyansh GargShuvam ChakrabortyChris CundyJiaming SongStefano ErmonPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- cooperative
- learning agent
- hierarchical reinforcement learning
- learning algorithm
- imitation learning
- state space
- model free
- multi agent
- search space
- dynamic programming
- optimal policy
- function approximation
- learning rate
- reinforcement learning algorithms
- search algorithm
- stochastic approximation
- data sets