Festivus

policy

LLaDA-8B-BGPO-countdown

THU-KEG · PyTorch

or hover any field below to flag it

Overview

Name
LLaDA-8B-BGPO-countdown
Author
THU-KEG
Framework
PyTorch
License
apache-2.0
Skill type
other
Evidence level
reported
Task description
Policy model from THU-KEG. Tags: safetensors, llada, reinforcement-learning, planning, countdown.

Spaces

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

Links

HuggingFace repo
THU-KEG/LLaDA-8B-BGPO-countdown
Paper (arXiv)
https://arxiv.org/abs/2510.11683

Compatible robots

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

Compatible environments

0

No environments list LLaDA-8B-BGPO-countdown yet.

Datasets that reference this policy

0

No datasets reference LLaDA-8B-BGPO-countdown yet.