gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-08-02 06:16:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

MuJoCo/Ant clarify the lack of use_contact_forces on v3 (and older) (#342)

Browse Source
This commit is contained in:
Kallinteris Andreas
2023-02-21 19:18:16 +02:00
committed by GitHub
parent d32bc80325
commit 2f42af629b
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
gymnasium/envs/mujoco/ant_v4.py
View File

@@ -84,7 +84,7 @@ class AntEnv(MujocoEnv, utils.EzPickle):
| 26 |angular velocity of the angle between back right links | -Inf | Inf | ankle_4 (right_back_leg) | hinge | angle (rad) |
If `use_contact_forces` is `True` then the observation space is extended by 14*6 = 84 elements, which are contact forces
If version < `v4` or `use_contact_forces` is `True` then the observation space is extended by 14*6 = 84 elements, which are contact forces
(external forces - force x, y, z and torque x, y, z) applied to the
center of mass of each of the links. The 14 links are: the ground link,
the torso link, and 3 links for each leg (1 + 1 + 12) with the 6 external forces.
@@ -116,7 +116,7 @@ class AntEnv(MujocoEnv, utils.EzPickle):
The total reward returned is ***reward*** *=* *healthy_reward + forward_reward - ctrl_cost*.
But if `use_contact_forces=True`
But if `use_contact_forces=True` or version < `v4`
The total reward returned is ***reward*** *=* *healthy_reward + forward_reward - ctrl_cost - contact_cost*.
In either case `info` will also contain the individual reward terms.