Here's the extensive experimental results of applying GAIL/BC on Mujoco environments, including Hopper-v1, Walker2d-v1, HalfCheetah-v1, Humanoid-v1, HumanoidStandup-v1. Every imitator is evaluated with seed to be 0.
- Hoppers-v1
- HalfCheetah-v1
- Walker2d-v1
- Humanoid-v1
- HumanoidStandup-v1
For details (e.g., adversarial loss, discriminator accuracy, etc.) about GAIL training, please see here
Un-normalized | Normalized | |
---|---|---|
Hopper-v1 | ||
HalfCheetah-v1 | ||
Walker2d-v1 | ||
Humanoid-v1 | ||
HumanoidStandup-v1 |
Un-normalized | Normalized | |
---|---|---|
Hopper-v1 | ||
HalfCheetah-v1 | ||
Walker2d-v1 | ||
Humanoid-v1 | ||
HumanoidStandup-v1 |
For all environments, the imitator is trained with 1, 5, 10, 50 trajectories, where each trajectory contains at most 1024 transitions, and seed 0, 1, 2, 3, respectively.
All BC imitators are trained with seed 0.