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

Calibrate your listeners! Robust communication-based training for pragmatic speakers. Findings of EMNLP 2021.

CSAC - Collaborative Semantic Aggregation and Calibration for Separated Domain Generalization

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

This repository contains code released by Google Research.

Code for `BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery`, Neurips 2021

DSL for matching Python ASTs

TUPÃ was developed to analyze electric field properties in molecular simulations

Benchmark tools for Compressive LiDAR-to-map registration

Code for the paper "Reinforcement Learning as One Big Sequence Modeling Problem"

[ICLR2021oral] Rethinking Architecture Selection in Differentiable NAS

Code for the KDD 2021 paper 'Filtration Curves for Graph Representation'

PyTorch implementation of Self-supervised Contrastive Regularization for DG (SelfReg)

Self-supervised learning optimally robust representations for domain generalization.

PyTorch implementation of the paper Ultra Fast Structure-aware Deep Lane Detection

torchbearer: A model fitting library for PyTorch

Code and dataset for AAAI 2021 paper FixMyPose: Pose Correctional Describing and Retrieval Hyounghun Kim, Abhay Zala, Graham Burri, Mohit Bansal.

Studying Python release adoptions by looking at PyPI downloads

My implementation of DeepMind's Perceiver

A Simplied Framework of GAN Inversion

Baseline and template code for node21 detection track