|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
|
- Set-up: Physics-based Humanoids agents with 26 degrees of freedom. These DOFs |
|
|
|
- Set-up: Physics-based Humanoid agents with 26 degrees of freedom. These DOFs |
|
|
|
- Agents: The environment contains 11 independent agents with same Behavior |
|
|
|
- `WalkerStatic` - Goal direction is always forward. |
|
|
|
- `WalkerDynamic`- Goal direction is randomized. |
|
|
|
- Agents: The environment contains 10 independent agents with same Behavior |
|
|
|
- +0.03 times body velocity in the goal direction. |
|
|
|
- +0.01 times head y position. |
|
|
|
- +0.01 times body direction alignment with goal direction. |
|
|
|
- -0.01 times head velocity difference from body velocity. |
|
|
|
- +0.02 times body velocity in the goal direction. (run towards target) |
|
|
|
- +0.01 times head direction alignment with goal direction. (face towards target) |
|
|
|
- +0.005 times head y position - left foot y position. (encourage head height) |
|
|
|
- +0.005 times head y position - right foot y position. (encourage head height) |
|
|
|
- Vector Observation space: 215 variables corresponding to position, rotation, |
|
|
|
- Vector Observation space: 236 variables corresponding to position, rotation, |
|
|
|
rotations applicable to the joints. |
|
|
|
rotations and strength applicable to the joints. |
|
|
|
- Visual Observations: None |
|
|
|
- Float Properties: Four |
|
|
|
- gravity: Magnitude of gravity |
|
|
|
|
|
|
|
- Default: 10 |
|
|
|
- Recommended Minimum: 3 |
|
|
|
- Recommended Maximum: 20 |
|
|
|
- Benchmark Mean Reward: 1000 |
|
|
|
- Benchmark Mean Reward for `WalkerStatic`: 1500 |
|
|
|
- Benchmark Mean Reward for `WalkerDynamic`: 700 |
|
|
|
|
|
|
|
## Pyramids |
|
|
|
|
|
|
|
|
GitHub