Primal Wasserstein Imitation Learning, or PWIL, is a method for imitation learning which ties to the primal form of the Wasserstein distance between the expert and the agent state-action distributions. The reward function is derived offline, as opposed to recent adversarial IL algorithms that learn a reward function through interactions with the environment, and requires little fine-tuning.
Source: Primal Wasserstein Imitation LearningPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Imitation Learning | 3 | 37.50% |
Decision Making | 2 | 25.00% |
Reinforcement Learning (RL) | 2 | 25.00% |
Continuous Control | 1 | 12.50% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |