policy
Mujoco_Ant_RL_with_Injury
DavidPrivateProjects · PyTorch
or hover any field below to flag it
Overview
Name
Mujoco_Ant_RL_with_Injury
Author
DavidPrivateProjects
Framework
PyTorch
License
unknown
Skill type
navigation
Evidence level
untested
Task description
This project explores how MuJoCo agents trained with the SAC algorithm adapt to injuries: modeled as changes in the action space—and how quickly they can regain a target level of performance through retraining.
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list Mujoco_Ant_RL_with_Injury yet.
Datasets that reference this policy
0No datasets reference Mujoco_Ant_RL_with_Injury yet.