Festivus

policy

qwen3-4b-dw-lr-dpo-offline

CEIA-RL · PyTorch

or hover any field below to flag it

Overview

Name
qwen3-4b-dw-lr-dpo-offline
Author
CEIA-RL
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Policy model from CEIA-RL. Tags: transformers, safetensors, qwen3, text-generation, generated_from_trainer.

Spaces

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

Links

HuggingFace repo
CEIA-RL/qwen3-4b-dw-lr-dpo-offline
Paper (arXiv)
https://arxiv.org/abs/2305.18290

Compatible robots

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

Compatible environments

0

No environments list qwen3-4b-dw-lr-dpo-offline yet.

Datasets that reference this policy

0

No datasets reference qwen3-4b-dw-lr-dpo-offline yet.