Muti-branch-DDPG-CARLA
Muti-branch-DDPG-CARLA copied to clipboard
Checkpoint
Hi, thanks for sharing and all the efforts. To make sure is the available checkpoint ("image_agent/ckpt"), the retrained model for CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving paper or it is same with CoRL-2017 model?
OK, it seems it is same as CoRL-2017. Do you have any pre-trained model for CIRL capable of achieving the same performance as the paper? If yes, would you please share it? If no, why? Are there any re-implementation issues?