Follow
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization. (arXiv:2006.13258v1 [cs.LG]) http://arxiv.org/abs/2006.13258
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization. (arXiv:2006.13258v1 [cs.LG]) http://arxiv.org/abs/2006.13258