frainer/task1_goalconditioned_envstate

1---2datasets: frainer/Task1_goalconditioned_envstate3library_name: lerobot4license: apache-2.05model_name: act6pipeline_tag: robotics7tags:8- robotics9- act10- lerobot11---12 13# Model Card for act14 15<!-- Provide a quick summary of what the model is/does. -->16 17 18[Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.19 20 21This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).22See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).23 24---25 26## How to Get Started with the Model27 28For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).29Below is the short version on how to train and run inference/eval:30 31### Train from scratch32 33```bash34lerobot-train \35  --dataset.repo_id=${HF_USER}/<dataset> \36  --policy.type=act \37  --output_dir=outputs/train/<desired_policy_repo_id> \38  --job_name=lerobot_training \39  --policy.device=cuda \40  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>41  --wandb.enable=true42```43 44_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._45 46### Evaluate the policy/run inference47 48```bash49lerobot-record \50  --robot.type=so100_follower \51  --dataset.repo_id=<hf_user>/eval_<dataset> \52  --policy.path=<hf_user>/<desired_policy_repo_id> \53  --episodes=1054```55 56Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.57 58---59 60## Model Details61 62- **License:** apache-2.0