Festivus

policy

ncp-qwen25-7b-lengthpenalty

agurung · PyTorch

or hover any field below to flag it

Overview

Name
ncp-qwen25-7b-lengthpenalty
Author
agurung
Framework
PyTorch
License
apache-2.0
Skill type
locomotion
Evidence level
reported
Task description
Policy model from agurung. Tags: safetensors, qwen2, reinforcement-learning, grpo, ncp.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
agurung/ncp-qwen25-7b-lengthpenalty
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet
SpotBoston DynamicsT1Booster RoboticsApolloApptronik

Compatible environments

0

No environments list ncp-qwen25-7b-lengthpenalty yet.

Datasets that reference this policy

0

No datasets reference ncp-qwen25-7b-lengthpenalty yet.