policy
Rebalance-----ML-in-Unity
JaxSulav · JAX
or hover any field below to flag it
Overview
Name
Rebalance-----ML-in-Unity
Author
JaxSulav
Framework
JAX
License
unknown
Skill type
other
Evidence level
untested
Task description
Using Reinforcement Learning to train a piece of floor to balance a ball over it. The PPO (Proximal Policy Optimization) algorithm is used to train the agent. Training process took around half hour with Tensorflow API in CPU and was trained up to 500,000 steps..
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 Rebalance-----ML-in-Unity yet.
Datasets that reference this policy
0No datasets reference Rebalance-----ML-in-Unity yet.