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

A minimalist tool to display a network graph.

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

A Multi-modal Model Chinese Spell Checker Released on ACL2021.

GazeScroller - Using Facial Movements to perform Hands-free Gesture on the system

This repository is a series of notebooks that show solutions for the projects at Dataquest.io.

Repository for the semantic WMI loss

Python program that works as a contact list

D2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection

Generating Digital Painting Lighting Effects via RGB-space Geometry (SIGGRAPH2020/TOG2020)

Implementation of FitVid video prediction model in JAX/Flax.

Website which uses Deep Learning to generate horror stories.

Official Implementation of LARGE: Latent-Based Regression through GAN Semantics

Pytorch implementation of Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization https://arxiv.org/abs/2008.11646

Starter Code for VALUE benchmark

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

SAT Project - The first project I had done at General Assembly, performed EDA, data cleaning and created data visualizations

Modifications of the official PyTorch implementation of StyleGAN3. Let's easily generate images and videos with StyleGAN2/2-ADA/3!

TLXZoo - Pre-trained models based on TensorLayerX

Contrastive Learning for Compact Single Image Dehazing, CVPR2021

Reviving Iterative Training with Mask Guidance for Interactive Segmentation