ZibinDong/ActionCodec-Base

Model Card for Model ID

Model Details

Model Description

ActionCodec model trained on 3 embodiments:

• franka_libero_20hz_1s
• widowx_bridge_5hz_3s
• franka_droid_15hz_1s

Model Sources [optional]

TODO

Uses

Direct Use

import numpy as np
from transformers import AutoModel
np.set_printoptions(suppress=True)
if __name__ == "__main__":
    tokenizer = AutoModel.from_pretrained("ZibinDong/ActionCodec-Base", trust_remote_code=True)
    q99 = np.array([0.9375, 0.91071427, 0.9375, 0.20357142, 0.26357144, 0.375, 1.0])
    q01 = np.array([-0.87857145, -0.87589288, -0.9375, -0.15107143, -0.20678571, -0.27964285, 0.0])
    # an example action from physical-intelligence/libero
    action = np.array(
        [
            [0.3268, 0.2089, -0.3295, 0.0000, -0.0868, -0.0611, 1.0000],
            [0.3696, 0.1955, -0.2866, 0.0000, -0.0793, -0.0643, 1.0000],
            [0.3857, 0.1929, -0.2759, 0.0000, -0.0782, -0.0654, 1.0000],
            [0.3964, 0.2089, -0.2786, 0.0000, -0.0761, -0.0654, 1.0000],
            [0.3321, 0.1741, -0.3268, 0.0000, -0.0793, -0.0686, 1.0000],
            [0.2250, 0.0964, -0.4232, 0.0000, -0.0932, -0.0761, 1.0000],
            [0.0723, 0.0000, -0.5625, 0.0000, -0.1339, -0.0879, 1.0000],
            [0.0536, 0.0000, -0.5652, 0.0000, -0.1521, -0.0921, 1.0000],
            [0.0750, 0.0000, -0.5464, 0.0000, -0.1511, -0.0964, 1.0000],
            [0.0723, 0.0000, -0.5411, 0.0000, -0.1414, -0.0986, 1.0000],
            [0.0402, 0.0000, -0.5196, 0.0000, -0.1350, -0.1007, 1.0000],
            [0.0080, 0.0000, -0.4795, 0.0000, -0.1189, -0.1018, 1.0000],
            [0.0000, 0.0000, -0.4527, 0.0000, -0.0986, -0.1018, 1.0000],
            [0.0000, 0.0000, -0.4313, 0.0000, -0.0846, -0.1018, 1.0000],
            [-0.0455, -0.0268, -0.3509, 0.0000, -0.0568, -0.1018, 1.0000],
            [-0.0964, -0.0482, -0.3321, 0.0000, -0.0439, -0.1039, 1.0000],
            [-0.1768, -0.0562, -0.3402, 0.0000, -0.0300, -0.1050, 1.0000],
            [-0.2438, -0.0429, -0.3187, 0.0000, -0.0193, -0.0996, 1.0000],
            [-0.3054, -0.0054, -0.2893, 0.0000, -0.0139, -0.0932, 1.0000],
            [-0.3509, 0.0000, -0.2598, 0.0000, -0.0054, -0.0879, 1.0000],
        ],
    )[None]
    # normalization
    normalized_action = np.copy(action)
    normalized_action[..., :-1] = normalized_action[..., :-1] / np.maximum(np.abs(q99), np.abs(q01))[..., :-1]
    normalized_action[..., -1] = normalized_action[..., -1] * 2.0 - 1.0  # scale to [-1, 1]
    normalized_action = normalized_action.clip(-1.0, 1.0)
    # tokenization
    tokens = tokenizer.encode(normalized_action)  # numpy (b, n, d) -> list of ints
    print(tokens)
    # decoding
    decoded_action, padding_mask = tokenizer.decode(tokens)  # list of ints -> numpy (b, n, d)
    # calculate reconstruction error
    mse_error = np.mean((normalized_action - decoded_action) ** 2)
    l1_error = np.mean(np.abs(normalized_action - decoded_action))
    print(f"Reconstruction MSE error: {mse_error:.6f}")
    print(f"Reconstruction L1 error: {l1_error:.6f}")

Downstream Use [optional]

TODO

Out-of-Scope Use

TODO

Bias, Risks, and Limitations

TODO

Recommendations

TODO

How to Get Started with the Model

Use the code below to get started with the model.

TODO

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]