Unofficial implementation of GfR and HIL hybrid motion imitation frameworks for Unitree G1 humanoid robot, enabling box climbing and box moving tasks via a two-stage training that combines reference tracking and general reinforcement learning.
41
No data
0
0
Apache-2.0
2026-07-27
Introduces a novel hybrid learning approach where the actor policy is conditioned on task goals rather than reference motions, allowing the learned behavior to generalize to new task conditions from a small set of reference trajectories.
Box Moving
Box Climbing
This is an unofficial implementation and extension of GfR and HIL, built on top of Holosoma. It is not the official code release for either paper.
This release provides two tasks for the 29-DoF Unitree G1:
exp:g1-29dof-wbt-hybrid-climb
exp:g1-29dof-wbt-hybrid-object
The same hybrid learning framework is used for both box climbing and box moving. Its key ideas are:
The actor does not observe the target reference motion. We find that this design can achieve high-quality motion tracking across a wide range of tasks; see the HIL paper for more details. The actor only observes the robot state and sparse task conditions or goals, while the reference motion is used to define the goals and tracking rewards. Because the policy is conditioned on task goals rather than a reference motion, the learned behavior can easily transfer to new task conditions.
Training combines two types of environments.
One policy is jointly optimized on two types of environments. The actor always uses the same observation interface across track and general RL envs, while the critic receives task-specific privileged information. This allows behavior learned from a small reference set to generalize to a wide range of task conditions and goals.
Run from the repository root:
bash scripts/setup_isaacsim.sh
source scripts/source_isaacsim_setup.sh
wandb login
Training uses two stages:
CUDA_VISIBLE_DEVICES=0 \
python src/holosoma/holosoma/train_agent.py \
exp:g1-29dof-wbt-hybrid-climb \
logger:wandb \
--training.num-envs=8192 \
--algo.config.num-learning-iterations=15000 \
--simul
Unofficial implementation and extension of GfR (RSS 2026) and HIL (TOG 2026)
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.