Closed HubFire closed 5 years ago
I wang to implement paper "CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving". In CIL DDPG agent,there have multi-branches output ,how to compute the policy gradient?
https://github.com/HubFire/Muti-branch-DDPG-CARLA A tensorflow implemention
I wang to implement paper "CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving". In CIL DDPG agent,there have multi-branches output ,how to compute the policy gradient?