Training code and evaluation benchmarks for the "Self-Supervised Policy Adaptation during Deployment" paper.

Last update: Nov 01, 2022

Overview

Self-Supervised Policy Adaptation during Deployment

PyTorch implementation of PAD and evaluation benchmarks from

Self-Supervised Policy Adaptation during Deployment

Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang

[Paper] [Website]

Citation

If you find our work useful in your research, please consider citing the paper as follows:

@article{hansen2020deployment,
  title={Self-Supervised Policy Adaptation during Deployment},
  author={Nicklas Hansen and Rishabh Jangir and Yu Sun and Guillem Alenyà and Pieter Abbeel and Alexei A. Efros and Lerrel Pinto and Xiaolong Wang},
  year={2020},
  eprint={2007.04309},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}

Setup

We assume that you have access to a GPU with CUDA >=9.2 support. All dependencies can then be installed with the following commands:

conda env create -f setup/conda.yml
conda activate pad
sh setup/install_envs.sh

Training & Evaluation

We have prepared training and evaluation scripts that can be run by sh scripts/train.sh and sh scripts/eval.sh. Alternatively, you can call the python scripts directly, e.g. for training call

CUDA_VISIBLE_DEVICES=0 python3 src/train.py \
    --domain_name cartpole \
    --task_name swingup \
    --action_repeat 8 \
    --mode train \
    --use_inv \
    --num_shared_layers 8 \
    --seed 0 \
    --work_dir logs/cartpole_swingup/inv/0 \
    --save_model

which should give you an output of the form

| train | E: 1 | S: 1000 | D: 0.8 s | R: 0.0000 | BR: 0.0000 | 
  ALOSS: 0.0000 | CLOSS: 0.0000 | RLOSS: 0.0000

We provide a pre-trained model that can be used for evaluation. To run Policy Adaptation during Deployment, call

CUDA_VISIBLE_DEVICES=0 python3 src/eval.py \
    --domain_name cartpole \
    --task_name swingup \
    --action_repeat 8 \
    --mode color_hard \
    --use_inv \
    --num_shared_layers 8 \
    --seed 0 \
    --work_dir logs/cartpole_swingup/inv/0 \
    --pad_checkpoint 500k

which should give you an output of the form

Evaluating logs/cartpole_swingup/inv/0 for 100 episodes (mode: color_hard)
eval reward: 666

Policy Adaptation during Deployment of logs/cartpole_swingup/inv/0 for 100 episodes (mode: color_hard)
pad reward: 722

Here's a few samples from the training and test environments of our benchmark:

Please refer to the project page and paper for results and experimental details.

Acknowledgements

We want to thank the numerous researchers and engineers involved in work of which this implementation is based on. Our SAC implementation is based on this repository, the original DeepMind Control suite is available here and the gym wrapper for it is available here. Go check them out!

Training code and evaluation benchmarks for the "Self-Supervised Policy Adaptation during Deployment" paper.

Related tags

Overview

Self-Supervised Policy Adaptation during Deployment

Citation

Setup

Training & Evaluation

Acknowledgements

Owner

Nicklas Hansen

[NIPS 2021] UOTA: Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration.

PyTorch implementation of the end-to-end coreference resolution model with different higher-order inference methods.

A powerful framework for decentralized federated learning with user-defined communication topology

PyTorch implementation of our ICCV paper DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection.

Dataset para entrenamiento de yoloV3 para 4 clases

一个多语言支持、易使用的 OCR 项目。An easy-to-use OCR project with multilingual support.

RobustVideoMatting and background composing in one model by using onnxruntime.

Joint Gaussian Graphical Model Estimation: A Survey

KoCLIP: Korean port of OpenAI CLIP, in Flax

Models, datasets and tools for Facial keypoints detection

This is the first released system towards complex meters` detection and recognition, which is implemented by computer vision techniques.

A PyTorch implementation of the Transformer model in "Attention is All You Need".

ICCV2021 Oral SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks

Official implementation of Deep Convolutional Dictionary Learning for Image Denoising.

A highly efficient, fast, powerful and light-weight anime downloader and streamer for your favorite anime.

Real-time object detection on Android using the YOLO network with TensorFlow

Starter kit for getting started in the Music Demixing Challenge.

Official PyTorch implementation of paper: Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation (ICCV 2021 Oral Presentation)

[ICCV2021] Official Pytorch implementation for SDGZSL (Semantics Disentangling for Generalized Zero-Shot Learning)

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers