Robotics
ONNX
LeRobot
rsl_rl
isaaclab
isaac-sim
strands-robots
reinforcement-learning
franka
reach
ppo
agents
sim2sim
Eval Results (legacy)
Instructions to use cagataydev/strands-isaaclab-reach-franka-policy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use cagataydev/strands-isaaclab-reach-franka-policy with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download sim2sim_mujoco.json from cagataydev/strands-isaaclab-reach-franka-policy: direct link, hf CLI and curl.
- Browser
- Download file 4.42 kB
-
https://huggingface.co/cagataydev/strands-isaaclab-reach-franka-policy/resolve/main/sim2sim_mujoco.json
- Command line
-
hf download hf://cagataydev/strands-isaaclab-reach-franka-policy/sim2sim_mujoco.json
-
curl -L -o sim2sim_mujoco.json https://huggingface.co/cagataydev/strands-isaaclab-reach-franka-policy/resolve/main/sim2sim_mujoco.json
4.42 kB
| { | |
| "jit": "runs/c3_agent_sweep/1e-3_s1/logs/rsl_rl/reach_franka/2026-09-29_05-04-21_isaaclab-20260929-050417-05a8c9c0dbae/exported/policy.pt", | |
| "episodes": 12, | |
| "seconds": 4.0, | |
| "seed": 0, | |
| "camera": "{'status': 'success', 'content': [{'text': \"Camera 'front' added at [1.6, 0.9, 0.9]\"}]}", | |
| "start_recording": "{'status': 'success', 'content': [{'text': \"Recording to LeRobotDataset: cagataydev/strands-isaaclab-reach-franka-mujoco-sim2sim\\n9 joints, 1 camera ['front'] @ 30fps\\nCodec: h264 | Task: reach the commanded end-effector pose\\nFrames are captured by a policy rollout - run_policy (one rollout; it closes NO episode, so call reset between rollouts or pass n_episodes=N in one call, else consecutive ro", | |
| "run_policy": "{'status': 'success', 'content': [{'text': 'Multi-episode run_policy: 12/12 episode(s) completed, 12 flushed to dataset, 1440 total steps.'}, {'json': {'robot_name': 'arm', 'policy': 'IsaacReachOnStrands', 'instruction': 'reach the commanded end-effector pose', 'n_episodes_requested': 12, 'n_episodes_completed': 12, 'episodes_saved': 12, 'dataset_episode_indices': [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11], 'total_steps': 1440, 'steps_used': 1440, 'stopped_reason': 'budget', 'stopped_reasons': ['budget', 'budget', 'budget', 'budget', 'budget', 'budget', 'budget', 'budget', 'budget', 'budget', 'budget', 'budget'], 'positional_fallback_used': False, 'generic_state_keys_used': False, 'missing_state_keys_used': False, 'policy_load_time_s': 0.0, 'policy_load_cache_hit': False, 'policy_resident_rss_mb': 1338.1328125, 'episodes': [{'episode': 0, 'robot_name': 'arm', 'policy': 'IsaacReachOnStrands', 'instruction': 'reach the commanded end-effector pose', 'instruction_read': True, 'n_steps': 120, 'steps_used': 120, 'elapsed_s': 0.916, 'stopped_early': False, 'stopped_reason': 'budget', 'stop_when_true_at_reset': False, 'stop_when_reset_warning': None, 'action_errors': 0, 'actions_applied': 120, 'video_path': None, 'video_frames': 0, 'video_fps': None, 'policy_load_time_s': 0.0, 'policy_load_cache_hit': False, 'positional_fallback_used': False, 'generic_state_keys_used': False, 'missing_state_keys_used': False, 'policy_resident_rss_mb': 1316.30859375, 'sim_time_s': 4.0, 'rtc_async_enabled'", | |
| "stop_recording": "{'status': 'success', 'content': [{'text': 'Episode saved to LeRobotDataset\\ncagataydev/strands-isaaclab-reach-franka-mujoco-sim2sim -- 1440 frames, 12 episode(s)\\nLocal: rec/reach-franka-mujoco/ds'}, {'json': {'repo_id': 'cagataydev/strands-isaaclab-reach-franka-mujoco-sim2sim', 'frame_count': 1440, 'episode_count': 12, 'parquet_episode_count': 12, 'episode_count_mismatch': False, 'dropped_frame_count': 0, 'root': 'rec/reach-franka-mujoco/ds'}}]}", | |
| "wall_s": 8.5, | |
| "episodes_eval": [ | |
| { | |
| "final_pos_err_m": 0.0715, | |
| "final_ori_err_rad": 0.115, | |
| "min_pos_err_m": 0.0389, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.0352, | |
| "final_ori_err_rad": 0.047, | |
| "min_pos_err_m": 0.0119, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.0234, | |
| "final_ori_err_rad": 0.195, | |
| "min_pos_err_m": 0.0152, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.3028, | |
| "final_ori_err_rad": 0.426, | |
| "min_pos_err_m": 0.0386, | |
| "success": false, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.1008, | |
| "final_ori_err_rad": 0.194, | |
| "min_pos_err_m": 0.0138, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.129, | |
| "final_ori_err_rad": 0.168, | |
| "min_pos_err_m": 0.0023, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.3414, | |
| "final_ori_err_rad": 0.309, | |
| "min_pos_err_m": 0.2083, | |
| "success": false, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.0278, | |
| "final_ori_err_rad": 0.099, | |
| "min_pos_err_m": 0.0169, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.0462, | |
| "final_ori_err_rad": 0.122, | |
| "min_pos_err_m": 0.0086, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.1243, | |
| "final_ori_err_rad": 0.111, | |
| "min_pos_err_m": 0.0076, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.0424, | |
| "final_ori_err_rad": 0.159, | |
| "min_pos_err_m": 0.0212, | |
| "success": true, | |
| "steps": 120 | |
| }, | |
| { | |
| "final_pos_err_m": 0.0263, | |
| "final_ori_err_rad": 0.091, | |
| "min_pos_err_m": 0.0068, | |
| "success": true, | |
| "steps": 120 | |
| } | |
| ], | |
| "success_rate": 0.833, | |
| "mean_final_pos_err_m": 0.1059 | |
| } |