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

AI Flow is an open source framework that bridges big data and artificial intelligence.

Official repository for the paper F, B, Alpha Matting

rastrainer is a QGIS plugin to training remote sensing semantic segmentation model based on PaddlePaddle.

⚡ H2G-Net for Semantic Segmentation of Histopathological Images

This is an example of object detection on Micro bacterium tuberculosis using Mask-RCNN

Model of an AI powered sign language interpreter.

Statsmodels: statistical modeling and econometrics in Python

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection, AAAI 2021.

Image-to-image translation with conditional adversarial nets

Face Alignment using python

Finetune the base 64 px GLIDE-text2im model from OpenAI on your own image-text dataset

Detection of PCBA defect

Code for unmixing audio signals in four different stems "drums, bass, vocals, others". The code is adapted from "Jukebox: A Generative Model for Music"

Contrastive Fact Verification

Pretrained models for Jax/Haiku; MobileNet, ResNet, VGG, Xception.

Adversarial Reweighting for Partial Domain Adaptation

Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

AntiFuzz: Impeding Fuzzing Audits of Binary Executables

Face recognize and crop them

Code for "PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation" CVPR 2019 oral