Update README.md

README.md

@@ -1,178 +1,233 @@
 ---
+
 datasets:
-- lerobot/aloha_sim_insertion_human
+
+  - lerobot/pusht
+
 library_name: lerobot
+
 license: apache-2.0
+
 model_name: diffusion
+
 pipeline_tag: robotics
+
 tags:
-- lerobot
-- robotics
-- diffusion
-- aloha
-- imitation-learning
-- benchmark
+
+  - lerobot
+
+  - robotics
+
+  - diffusion
+
+  - pusht
+
+  - imitation-learning
+
+  - benchmark
+
 ---
 
-# 🦾 Diffusion Policy for Aloha Insertion (200k Steps)
+
+
+# 🦾 Diffusion Policy for Push-T (200k Steps)
+
+
 
 [![LeRobot](https://img.shields.io/badge/Library-LeRobot-yellow)](https://github.com/huggingface/lerobot)
-[![Task](https://img.shields.io/badge/Task-Aloha_Insertion-blue)](https://huggingface.co/datasets/lerobot/aloha_sim_insertion_human)
+
+[![Task](https://img.shields.io/badge/Task-Push--T-blue)](https://huggingface.co/datasets/lerobot/pusht)
+
 [![UESTC](https://img.shields.io/badge/Author-UESTC_Graduate-red)](https://www.uestc.edu.cn/)
+
 [![License](https://img.shields.io/badge/License-Apache_2.0-green)](https://www.apache.org/licenses/LICENSE-2.0)
 
-> **Summary:** This model represents a benchmark experiment for **Diffusion Policy** on the challenging **Aloha Insertion** task (Simulated). It was trained using the [LeRobot](https://github.com/huggingface/lerobot) framework to evaluate the algorithm's performance on complex, high-dimensional 3D manipulation tasks compared to baseline methods.
 
-- **🧩 Task**: Aloha Insertion (Simulated, 3D)
+
+> **Summary:** This model demonstrates the capabilities of **Diffusion Policy** on the precision-demanding **Push-T** task. It was trained using the [LeRobot](https://github.com/huggingface/lerobot) framework as part of a thesis research project benchmarking Imitation Learning algorithms.
+
+
+
+- **🧩 Task**: Push-T (Simulated)
+
 - **🧠 Algorithm**: [Diffusion Policy](https://huggingface.co/papers/2303.04137) (DDPM)
-- **🔄 Training Steps**: 200,000
+
+- **🔄 Training Steps**: 200,000 (Fine-tuned via Resume)
+
 - **🎓 Author**: Graduate Student, **UESTC** (University of Electronic Science and Technology of China)
 
+
+
 ---
 
+
+
 ## 🔬 Benchmark Results (vs ACT)
 
-This experiment highlights the significant difficulty of the Aloha Insertion task for generative policies under limited compute constraints (Batch Size=8). While the ACT baseline achieved a **2%** success rate (1/50), the Diffusion Policy focused on trajectory learning but struggled with the final insertion alignment.
+
+
+Compared to the ACT baseline (which achieved **0%** success rate in our controlled experiments), this Diffusion Policy model demonstrates significantly better control precision and trajectory stability.
+
+
 
 ### 📊 Evaluation Metrics (50 Episodes)
 
+
+
 | Metric | Value | Comparison to ACT Baseline | Status |
+
 | :--- | :---: | :--- | :---: |
-| **Success Rate** | **0.0%** | **Slightly Lower** (ACT: 2.0%) | 📉 |
-| **Avg Max Reward** | **0.10** | **Partial Success** (Grasping achieved) | 🚧 |
-| **Avg Sum Reward** | **8.20** | **Stable Trajectories** | ✅ |
 
-> **Note:** The Aloha Insertion task involves high-dimensional inputs (3 cameras) and precise 3D spatial reasoning. The results indicate that under low batch-size constraints (Batch Size=8), ACT's deterministic policy may converge faster than Diffusion Policy, which likely requires longer training or larger batches for this specific domain.
+| **Success Rate** | **14.0%** | **Significant Improvement** (ACT: 0%) | 🏆 |
+
+| **Avg Max Reward** | **0.81** | **+58% Higher Precision** (ACT: ~0.51) | 📈 |
+
+| **Avg Sum Reward** | **130.46** | **+147% More Stable** (ACT: ~52.7) | ✅ |
+
+
+
+> **Note:** The Push-T environment requires **>95% target coverage** for success. An average max reward of `0.81` indicates the policy consistently moves the block very close to the target position, proving strong manipulation capabilities despite the strict success threshold.
+
+
 
 ---
 
+
+
 ## ⚙️ Model Details
 
+
+
 | Parameter | Description |
+
 | :--- | :--- |
+
 | **Architecture** | ResNet18 (Vision Backbone) + U-Net (Diffusion Head) |
-| **Input** | 3 Camera Views (Top, Left, Right) |
+
 | **Prediction Horizon** | 16 steps |
+
 | **Observation History** | 2 steps |
+
 | **Action Steps** | 8 steps |
 
+
+
+- **Training Strategy**: 
+
+  - Phase 1: Initial training (100,000 steps) -> Model: `Lemon-03/DP_PushT_test`
+
+  - Phase 2: Resume/Fine-tuning (+100,000 steps) -> Model: `Lemon-03/DP_PushT_test_Resume`
+
+  - **Total**: 200,000 steps
+
+
+
+---
+
+
+
+## 🔧 Training Configuration (Reference)
+
+
+
+For reproducibility, here are the key parameters used during the training session:
+
+
+
+  - **Batch Size**: 64
+
+  - **Optimizer**: AdamW (`lr=1e-4`)
+
+  - **Scheduler**: Cosine with warmup
+
+  - **Vision**: ResNet18 with random crop (84x84)
+
+  - **Precision**: Mixed Precision (AMP) enabled
+
+
+
+#### Original Training Command (My Resume Mode)
+
+
+
+```bash
+
+python -m lerobot.scripts.lerobot_train \
+
+  --policy.type diffusion \
+
+  --env.type pusht \
+
+  --dataset.repo_id lerobot/pusht \
+
+  --wandb.enable true \
+
+  --eval.batch_size 8 \
+
+  --job_name DP_PushT_Resume \
+
+  --policy.repo_id Lemon-03/DP_PushT_test_Resume \
+
+  --policy.pretrained_path outputs/train/2025-12-02/14-33-35_DP_PushT/checkpoints/last/pretrained_model \
+
+  --steps 100000
+
+```
+
 ---
 
-## 🔧 Training Configuration
-
-For reproducibility, here are the key parameters used during the training session.
-
-- **Source**: Configuration adapted from [CSCSX/LeRobotTutorial-CN](https://github.com/CSCSX/LeRobotTutorial-CN).
-- **Batch Size**: 8 (Limited by 8GB VRAM)
-- **Optimizer**: AdamW (`lr=1e-4`)
-- **Scheduler**: Cosine with warmup
-- **Vision**: ResNet18 with GroupNorm (Cropped to 420x560)
-
-<details>
-<summary>📄 <strong>Click to view full <code>diffusion_aloha.yaml</code> used for training</strong></summary>
-
-```yaml
-# @package _global_
-
-# 随机种子
-seed: 100000
-job_name: Diffusion-Aloha-Insertion
-
-# 训练参数
-steps: 200000            # 原文件写的是 20万步 (Aloha 比较难练)
-eval_freq: 20000         # 稍微改频一点，方便看进度
-save_freq: 20000
-log_freq: 200
-batch_size: 8            # ⚠️ 关键：Aloha 必须用小 Batch，否则 8G 显存不够
-
-# 数据集
-dataset:
-  repo_id: lerobot/aloha_sim_insertion_human
-
-# 评估设置
-eval:
-  n_episodes: 50
-  batch_size: 8          # 保持与训练一致
-
-# 环境设置
-env:
-  type: aloha
-  task: AlohaInsertion-v0
-  fps: 50
-
-# 策略配置
-policy:
-  type: diffusion
-
-  # --- 视觉处理 ---
-  vision_backbone: resnet18
-  # Aloha 的图片是矩形的，这里使用特定的裁剪尺寸
-  crop_shape: [420, 560]
-  crop_is_random: true
-  pretrained_backbone_weights: null  # 原配置指定不加载预训练权重
-  use_group_norm: true
-  spatial_softmax_num_keypoints: 32
-
-  # --- Diffusion 核心架构 (U-Net) ---
-  down_dims: [512, 1024, 2048]
-  kernel_size: 5
-  n_groups: 8
-  diffusion_step_embed_dim: 128
-  use_film_scale_modulation: true
-
-  # --- 动作预测参数 ---
-  n_action_steps: 8
-  n_obs_steps: 2
-  horizon: 16
-
-  # --- 噪声调度器 (DDPM) ---
-  noise_scheduler_type: DDPM
-  num_train_timesteps: 100
-  num_inference_steps: 100
-  beta_schedule: squaredcos_cap_v2
-  beta_start: 0.0001
-  beta_end: 0.02
-  prediction_type: epsilon
-  clip_sample: true
-  clip_sample_range: 1.0
-
-  # --- 优化器 ---
-  optimizer_lr: 1e-4
-  optimizer_weight_decay: 1e-6
-  #grad_clip_norm: 10
-  
-  scheduler_name: cosine
-  scheduler_warmup_steps: 500
-
-  use_amp: true
-````
-
-\</details\>
-
------
+
 
 ## 🚀 Evaluate (My Evaluation Mode)
 
+
+
 Run the following command in your terminal to evaluate the model for 50 episodes and save the visualization videos:
 
+
+
 ```bash
+
 python -m lerobot.scripts.lerobot_eval \
+
   --policy.type diffusion \
-  --policy.pretrained_path Lemon-03/DP_Aloha_Insertion_test \
+
+  --policy.pretrained_path outputs/train/2025-12-04/14-47-37_DP_PushT_Resume/checkpoints/last/pretrained_model \
+
   --eval.n_episodes 50 \
-  --eval.batch_size 8 \
-  --env.type aloha \
-  --env.task AlohaInsertion-v0
+
+  --eval.batch_size 10 \
+
+  --env.type pusht \
+
+  --env.task PushT-v0
+
 ```
 
+
+
 To evaluate this model locally, run the following command:
 
+
+
 ```bash
+
 python -m lerobot.scripts.lerobot_eval \
+
   --policy.type diffusion \
-  --policy.pretrained_path Lemon-03/DP_Aloha_Insertion_test \
+
+  --policy.pretrained_path Lemon-03/DP_PushT_test_Resume \
+
   --eval.n_episodes 50 \
-  --eval.batch_size 8 \
-  --env.type aloha \
-  --env.task AlohaInsertion-v0
-```
+
+  --eval.batch_size 10 \
+
+  --env.type pusht \
+
+  --env.task PushT-v0
+
+```
+
+
+
+-----