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

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

一些经典的CTR算法的复现; LR, FM, FFM, AFM, DeepFM，xDeepFM, PNN, DCN, DCNv2, DIFM, AutoInt, FiBiNet,AFN,ONN,DIN, DIEN ... （pytorch, tf2.0）

Perfect implement. Model shared. x0.5 (Top1:60.646) and 1.0x (Top1:69.402).

Learning to Segment Instances in Videos with Spatial Propagation Network

[CVPR'21 Oral] Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning

Official page of Patchwork (RA-L'21 w/ IROS'21)

Technical Analysis Indicators - Pandas TA is an easy to use Python 3 Pandas Extension with 130+ Indicators

Converting CPT to bert form for use

Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation

UpChecker is a simple opensource project to host it fast on your server and check is server up, view statistic, get messages if it is down. UpChecker - just run file and use project easy

A simple library that implements CLIP guided loss in PyTorch.

PyTorch implementation of "Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning"

DLL: Direct Lidar Localization

用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本

DSTC10 Track 2 - Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations

SberSwap Video Swap base on deep learning

Code for the CIKM 2019 paper "DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting".

Spearmint Bayesian optimization codebase

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

repro_eval is a collection of measures to evaluate the reproducibility/replicability of system-oriented IR experiments