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

Rethinking Transformer-based Set Prediction for Object Detection

MoveNetを用いたPythonでの姿勢推定のデモ

EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale

Implementation of CVPR'2022:Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors

This is the code of "Multi-view Contrastive Graph Clustering" in NeurlPS 2021.

Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

Install alphafold on the local machine, get out of docker.

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite and .pb from .tflite.

A simple code to convert image format and channel as well as resizing and renaming multiple images.

SatelliteSfM - A library for solving the satellite structure from motion problem

Acute ischemic stroke dataset

🥇 LG-AI-Challenge 2022 1위 솔루션 입니다.

covid question answering datasets and fine tuned models

WORD: Revisiting Organs Segmentation in the Whole Abdominal Region

Rlmm blender toolkit - A set of tools to streamline level generation in UDK straight from Blender

This repo contains implementation of different architectures for emotion recognition in conversations.

Code for PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

Gym Threat Defense

Fast Soft Color Segmentation

Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral