PWIL
Primal Wasserstein Imitation Learning
2000년 도입 · 논문 3편에서 사용
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.
출처: Primal Wasserstein Imitation Learning
소개 논문: Primal Wasserstein Imitation Learning
Imitation Learning Methods · Reinforcement Learning