ACT on AlohaTransferCube, 80k steps, trained on Apple M4

README.md

@@ -0,0 +1,101 @@
+---
+library_name: lerobot
+license: mit
+pipeline_tag: robotics
+datasets:
+- lerobot/aloha_sim_transfer_cube_human
+tags:
+- robotics
+- lerobot
+- act
+- imitation-learning
+- aloha
+- simulation
+model-index:
+- name: act_aloha_sim_transfer_cube
+  results:
+  - task:
+      type: robotics
+      name: AlohaTransferCube-v0 (gym-aloha)
+    dataset:
+      type: lerobot/aloha_sim_transfer_cube_human
+      name: aloha_sim_transfer_cube_human
+    metrics:
+    - type: success_rate
+      value: 75.5
+      name: success rate over 200 episodes (95% Wilson CI 69.1-80.9)
+---
+
+# ACT on ALOHA TransferCube, trained from scratch on an Apple M4 laptop
+
+An [ACT](https://arxiv.org/abs/2304.13705) policy for the `AlohaTransferCube-v0` simulation task,
+trained with [LeRobot](https://github.com/huggingface/lerobot) 0.7.0 on the
+[`lerobot/aloha_sim_transfer_cube_human`](https://huggingface.co/datasets/lerobot/aloha_sim_transfer_cube_human)
+dataset (50 human demonstrations). Training ran on an Apple M4 MacBook Pro (MPS, no NVIDIA GPU) for
+80k steps at batch size 8, about 10 hours in total. LeRobot's default ACT hyperparameters, nothing tuned.
+
+Code, evaluation scripts, per-checkpoint results and training curves:
+[github.com/ChadSaglam/lerobot-sim-transfer-cube](https://github.com/ChadSaglam/lerobot-sim-transfer-cube).
+
+## Evaluation
+
+Same simulator, same episode seeds (`--seed=1000`), 200 episodes, 95% Wilson intervals from `lerobot-eval`.
+
+| Policy | Training steps | Success | 95% CI |
+|---|---|---|---|
+| official [`lerobot/act_aloha_sim_transfer_cube_human`](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human) | 80k | 81.0% (162/200) | 75.0-85.8 |
+| **this model** (seed 1000) | 80k | **75.5%** (151/200) | 69.1-80.9 |
+| same run at 50k steps | 50k | 64.0% (128/200) | 57.1-70.3 |
+| second seed (1001) at 50k steps | 50k | 62.0% (124/200) | 55.1-68.4 |
+
+The intervals of this model and the official checkpoint overlap; the two are statistically
+indistinguishable at this sample size. The 50k checkpoints are clearly below the baseline.
+
+Two things the per-checkpoint evaluations showed (details in the GitHub README):
+the training loss is not a proxy for task success (two seeds with identical loss curves differed by
+34 points in success at 10k steps), and 50-episode evaluations cannot rank neighbouring checkpoints.
+
+## How to use
+
+```bash
+pip install 'lerobot[aloha]==0.7.0'
+
+lerobot-eval \
+  --policy.path=ChadSaglam/act_aloha_sim_transfer_cube \
+  --env.type=aloha \
+  --env.task=AlohaTransferCube-v0 \
+  --eval.n_episodes=200 \
+  --eval.batch_size=10 \
+  --seed=1000 \
+  --policy.device=cuda          # mps on Apple Silicon; add --eval.use_async_envs=false on macOS
+```
+
+## Training
+
+```bash
+lerobot-train \
+  --policy.type=act \
+  --policy.device=mps \
+  --policy.push_to_hub=false \
+  --dataset.repo_id=lerobot/aloha_sim_transfer_cube_human \
+  --env.type=aloha \
+  --env.task=AlohaTransferCube-v0 \
+  --env_eval_freq=0 \
+  --seed=1000 \
+  --steps=50000 \
+  --batch_size=8 \
+  --save_freq=10000 \
+  --output_dir=outputs/train/act_transfer_cube_seed1000
+# then resumed from the 50k checkpoint with --resume=true --steps=80000
+```
+
+- Policy: ACT, ResNet-18 backbone (ImageNet init), chunk size 100, 100 action steps, VAE on, KL weight 10,
+  AdamW, learning rate 1e-5, batch size 8. `train_config.json` in this repository has every setting.
+- Throughput on the M4: 2.2 steps/s. 50k steps in 6 h 22 min, the 30k-step extension in 3 h 47 min.
+- Checkpoint format: LeRobot 0.7.0 processor pipeline (`policy_preprocessor.json`, `policy_postprocessor.json`).
+
+## Limitations
+
+- Simulation only; one task; one evaluation seed set. Another `--seed` would move every number by a few points.
+- Success is the `gym-aloha` definition (cube lifted by the right arm and transferred to the left gripper).
+- No hyperparameter tuning; LeRobot defaults throughout.

config.json

@@ -0,0 +1,66 @@
+{
+    "type": "act",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                14
+            ]
+        }
+    },
+    "device": "mps",
+    "dtype": null,
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "pretrained_revision": null,
+    "chunk_size": 100,
+    "n_action_steps": 100,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "vision_backbone": "resnet18",
+    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+    "replace_final_stride_with_dilation": 0,
+    "pre_norm": false,
+    "dim_model": 512,
+    "n_heads": 8,
+    "dim_feedforward": 3200,
+    "feedforward_activation": "relu",
+    "n_encoder_layers": 4,
+    "n_decoder_layers": 1,
+    "use_vae": true,
+    "latent_dim": 32,
+    "n_vae_encoder_layers": 4,
+    "temporal_ensemble_coeff": null,
+    "dropout": 0.1,
+    "kl_weight": 10.0,
+    "optimizer_lr": 1e-05,
+    "optimizer_weight_decay": 0.0001,
+    "optimizer_lr_backbone": 1e-05,
+    "optimizer_fused": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a38a4d96fc4fdcb6ff37e0b1aa3a23db165d5afb98f023282af311465c656d
+size 206765336

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              14
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:797777e6e870b9c70a950b6860aa23d246ee8292a6f10f4bca727ab564e39348
+size 3892

policy_preprocessor.json

@@ -0,0 +1,56 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "mps",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.top": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              14
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              14
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_3_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfee093c0b768d07b95824d3c670e35606ec969298df7ce7500a233bc1394058
+size 3860

train_config.json

@@ -0,0 +1,300 @@
+{
+    "dataset": {
+        "repo_id": "lerobot/aloha_sim_transfer_cube_human",
+        "repo_type": "dataset",
+        "root": null,
+        "episodes": null,
+        "exclude_episodes": null,
+        "image_transforms": {
+            "enable": false,
+            "backend": "dataloader",
+            "gpu_compile": true,
+            "gpu_chunk_size": 32,
+            "max_num_transforms": 3,
+            "random_order": false,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.05,
+                            0.05
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 1.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "affine": {
+                    "weight": 1.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            -5.0,
+                            5.0
+                        ],
+                        "translate": [
+                            0.05,
+                            0.05
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "streaming_episode_pool_size": null,
+        "streaming_sampling_strategy": "remaining",
+        "streaming_prefetch_episodes": 8,
+        "streaming_byte_budget_gb": 8.0,
+        "streaming_decode_threads": 2,
+        "streaming_decoded_queue_size": 8,
+        "streaming_native_http_connections": null,
+        "streaming_native_http_subranges": 1,
+        "streaming_sidecar_lock_timeout_s": 1800.0,
+        "video_decoder_cache_size": null,
+        "eval_split": 0.0
+    },
+    "env": {
+        "type": "aloha",
+        "task": "AlohaTransferCube-v0",
+        "fps": 50,
+        "features": {},
+        "features_map": {},
+        "max_parallel_tasks": 1,
+        "disable_env_checker": true,
+        "server": null,
+        "episode_length": 400,
+        "obs_type": "pixels_agent_pos",
+        "render_mode": "rgb_array"
+    },
+    "policy": {
+        "type": "act",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.top": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    14
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    14
+                ]
+            }
+        },
+        "device": "mps",
+        "dtype": null,
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "pretrained_revision": null,
+        "chunk_size": 100,
+        "n_action_steps": 100,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "vision_backbone": "resnet18",
+        "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+        "replace_final_stride_with_dilation": 0,
+        "pre_norm": false,
+        "dim_model": 512,
+        "n_heads": 8,
+        "dim_feedforward": 3200,
+        "feedforward_activation": "relu",
+        "n_encoder_layers": 4,
+        "n_decoder_layers": 1,
+        "use_vae": true,
+        "latent_dim": 32,
+        "n_vae_encoder_layers": 4,
+        "temporal_ensemble_coeff": null,
+        "dropout": 0.1,
+        "kl_weight": 10.0,
+        "optimizer_lr": 1e-05,
+        "optimizer_weight_decay": 0.0001,
+        "optimizer_lr_backbone": 1e-05,
+        "optimizer_fused": null
+    },
+    "reward_model": null,
+    "output_dir": "outputs/train/act_transfer_cube_seed1000",
+    "job_name": "act_transfer_cube_seed1000",
+    "resume": true,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "tf32": true,
+    "num_workers": 4,
+    "batch_size": 8,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 80000,
+    "env_eval_freq": 0,
+    "log_freq": 200,
+    "eval_steps": 0,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 10000,
+    "checkpoint_format": "safetensors",
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 1e-05,
+        "weight_decay": 0.0001,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08,
+        "fused": null
+    },
+    "scheduler": null,
+    "parallelism": {
+        "dp_replicate": 1,
+        "dp_shard": 1,
+        "context_parallel": {
+            "ring_degree": 1,
+            "ulysses_degree": 1
+        },
+        "cfg_parallel": 1
+    },
+    "accelerator": {
+        "mixed_precision": "no",
+        "gradient_accumulation": {
+            "steps": 1,
+            "sync_each_batch": false
+        },
+        "grad_scaler": {
+            "init_scale": 65536.0,
+            "growth_factor": 2.0,
+            "backoff_factor": 0.5,
+            "growth_interval": 2000
+        },
+        "fsdp": {
+            "reshard_after_forward": true,
+            "wrap_modules": null,
+            "min_num_params": null,
+            "cpu_offload": false,
+            "ignored_modules": null,
+            "mixed_precision_policy": {
+                "param_dtype": null,
+                "reduce_dtype": null,
+                "output_dtype": null,
+                "cast_forward_inputs": true
+            }
+        },
+        "ddp": {
+            "find_unused_parameters": true,
+            "gradient_as_bucket_view": false,
+            "static_graph": false
+        },
+        "init_process_group": {
+            "backend": "nccl",
+            "init_method": null,
+            "timeout": null
+        },
+        "compile": {
+            "enabled": false,
+            "backend": "inductor",
+            "mode": null,
+            "regional": true
+        },
+        "activation_checkpointing": {
+            "mode": "none"
+        }
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 9,
+        "use_async_envs": true,
+        "recording": false,
+        "recording_repo_id": null,
+        "recording_private": false,
+        "max_episode_steps": null
+    },
+    "ema": null,
+    "trackio": {
+        "enable": false,
+        "disable_artifact": true,
+        "project": "lerobot",
+        "space_id": null,
+        "private": null,
+        "run_name": null,
+        "resume": null,
+        "capture_console": true
+    },
+    "peft": null,
+    "job": {
+        "target": null,
+        "image": "huggingface/lerobot-gpu:latest",
+        "timeout": "2d",
+        "detach": false,
+        "tags": []
+    },
+    "save_checkpoint_to_hub": false,
+    "sample_weighting": null,
+    "rename_map": {},
+    "checkpoint_path": "outputs/train/act_transfer_cube_seed1000/checkpoints/last"
+}