policy

CDM

sirraya-labs · RLlib

or hover any field below to flag it

Overview

Name
CDM
Author
sirraya-labs
Framework
RLlib
License
MIT
Skill type
other
Evidence level
untested
Task description
Contraction Dynamics Model (CDM) is a novel reinforcement learning framework that integrates contraction theory with deep learning to produce mathematically-stable robot controllers. Unlike traditional RL approaches that only optimize for reward, CDM learns dynamics with built-in stability guarantee

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 CDM yet.

Datasets that reference this policy

0

No datasets reference CDM yet.