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 yet

Compatible environments

0

No environments list Mujoco_Ant_RL_with_Injury yet.

Datasets that reference this policy

0

No datasets reference Mujoco_Ant_RL_with_Injury yet.