Code base for reproducing results of I.Schubert, D.Driess, O.Oguz, and M.Toussaint: Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics. NeurIPS (2021)

Related tags

Deep Learningl2e
Overview

Learning to Execute (L2E)

Official code base for completely reproducing all results reported in

I.Schubert, D.Driess, O.Oguz, and M.Toussaint: Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics. NeurIPS (2021)

Installation

Initialize submodules:

git submodule init
git submodule update

Install rai-python

For rai-python, it is recommended to use this docker image.

If you want to install rai-python manually, follow instructions here. You will also need to install PhysX, ideally following these instructions.

Install gym-physx

Modify the path to rai-python/rai/rai/ry in gym-physx/gym_physx/envs/physx_pushing_env.py depending on your installation. Then install gym-physx using pip:

cd gym-physx
pip install .

Install gym-obstacles

In case you also want to run the 2D maze example with moving obstacles as introduced in section A.3, install gym-obstacles:

cd gym-obstacles
pip install .

Install our fork of stable-baselines3

cd stable-baselines3
pip install .

Reproduce figures

l2e/l2e/ contains code to reproduce the reults in the paper.

Figures consist of multiple experiments and are defined in plot_results.json.

Experiments are defined in config_$EXPERIMENT.json.

Intermediate and final results are saved to $scratch_root/$EXPERIMENT/ (configure $scratch_root in each config_$EXPERIMENT.json as well as in plot_results.json).

Step-by-step instructions to reproduce figures:

  1. Depending on experiment, use the following train scripts:

    1. For the RL runs ($EXPERIMENT=l2e* and $EXPERIMENT=her*)

      ./train.sh $EXPERIMENT
    2. For the Inverse Model runs ($EXPERIMENT=im_plan_basic and $EXPERIMENT=im_plan_obstacle_training)

      First collect data:

      ./imitation_data.sh $EXPERIMENT

      Then train inverse model

      ./imitation_learning.sh $EXPERIMENT
    3. For the Direct Execution runs ($EXPERIMENT=plan_basic and $EXPERIMENT=plan_obstacle)

      No training stage is needed here.

    ./train.sh $EXPERIMENT will launch multiple screens with multiple independent runs of $EXPERIMENT. The number of runs is configured using $AGENTS_MIN and $AGENTS_MAX in config_$EXPERIMENT.json.

    ./imitation_data.sh will launch $n_data_collect_workers workers for collecting data, and ./imitation_learning.sh will launch $n_training_workers runs training models independently.

  2. Evaluate results

    ./evaluate.sh $EXPERIMENT

    python evaluate.py $EXPERIMENT will launch multiple screens, one for each agent that was trained in step 1. python evaluate.py $EXPERIMENT will automatically scan for new training output, and only evaluate model checkpoints that haven't been evaluated yet.

  3. Plot results

    After all experiments are finished, create plots using

    python plot_results.py

    This will create all data figures contained in the paper. Figures are saved in l2e/figs/ (configure in plot_results.json)

Steerable discovery of neural audio effects

Steerable discovery of neural audio effects Christian J. Steinmetz and Joshua D. Reiss Abstract Applications of deep learning for audio effects often

Christian J. Steinmetz 182 Dec 29, 2022
Corruption Invariant Learning for Re-identification

Corruption Invariant Learning for Re-identification The official repository for Benchmarks for Corruption Invariant Person Re-identification (NeurIPS

Minghui Chen 73 Dec 08, 2022
Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions'

pytorch-inpainting-with-partial-conv Official implementation is released by the authors. Note that this is an ongoing re-implementation and I cannot f

Naoto Inoue 525 Jan 01, 2023
Source code for "Roto-translated Local Coordinate Framesfor Interacting Dynamical Systems"

Roto-translated Local Coordinate Frames for Interacting Dynamical Systems Source code for Roto-translated Local Coordinate Frames for Interacting Dyna

Miltiadis Kofinas 19 Nov 27, 2022
AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data

AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data [WIP] Unofficial Pytorch implementation of AdaSpeech 2. Requirements : All code written i

Rishikesh (ऋषिकेश) 63 Dec 28, 2022
Weakly Supervised Learning of Rigid 3D Scene Flow

Weakly Supervised Learning of Rigid 3D Scene Flow This repository provides code and data to train and evaluate a weakly supervised method for rigid 3D

Zan Gojcic 124 Dec 27, 2022
For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training.

LongScientificFormer For encoding a text longer than 512 tokens, for example 800. Set max_pos to 800 during both preprocessing and training. Some code

Athar Sefid 6 Nov 02, 2022
Learning Features with Parameter-Free Layers (ICLR 2022)

Learning Features with Parameter-Free Layers (ICLR 2022) Dongyoon Han, YoungJoon Yoo, Beomyoung Kim, Byeongho Heo | Paper NAVER AI Lab, NAVER CLOVA Up

NAVER AI 65 Dec 07, 2022
One-line your code easily but still with the fun of doing so!

One-liner-iser One-line your code easily but still with the fun of doing so! Have YOU ever wanted to write one-line Python code, but don't have the sa

5 May 04, 2022
UnpNet - Rethinking 3-D LiDAR Point Cloud Segmentation(IEEE TNNLS)

UnpNet Citation Please cite the following paper if you use this repository in your reseach. @article {PMID:34914599, Title = {Rethinking 3-D LiDAR Po

Shijie Li 4 Jul 15, 2022
Implementation of Nyström Self-attention, from the paper Nyströmformer

Nyström Attention Implementation of Nyström Self-attention, from the paper Nyströmformer. Yannic Kilcher video Install $ pip install nystrom-attention

Phil Wang 95 Jan 02, 2023
Learning Off-Policy with Online Planning, CoRL 2021

LOOP: Learning Off-Policy with Online Planning Accepted in Conference of Robot Learning (CoRL) 2021. Harshit Sikchi, Wenxuan Zhou, David Held Paper In

Harshit Sikchi 24 Nov 22, 2022
The authors' official PyTorch SigWGAN implementation

The authors' official PyTorch SigWGAN implementation This repository is the official implementation of [Sig-Wasserstein GANs for Time Series Generatio

9 Jun 16, 2022
SVG Icon processing tool for C++

BAWR This is a tool to automate the icons generation from sets of svg files into fonts and atlases. The main purpose of this tool is to add it to the

Frank David Martínez M 66 Dec 14, 2022
Vision-Language Transformer and Query Generation for Referring Segmentation (ICCV 2021)

Vision-Language Transformer and Query Generation for Referring Segmentation Please consider citing our paper in your publications if the project helps

Henghui Ding 143 Dec 23, 2022
AI grand challenge 2020 Repo (Speech Recognition Track)

KorBERT를 활용한 한국어 텍스트 기반 위협 상황인지(2020 인공지능 그랜드 챌린지) 본 프로젝트는 ETRI에서 제공된 한국어 korBERT 모델을 활용하여 폭력 기반 한국어 텍스트를 분류하는 다양한 분류 모델들을 제공합니다. 본 개발자들이 참여한 2020 인공지

Young-Seok Choi 23 Jan 25, 2022
Official code for our EMNLP2021 Outstanding Paper MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks

MindCraft Authors: Cristian-Paul Bara*, Sky CH-Wang*, Joyce Chai This is the official code repository for the paper (arXiv link): Cristian-Paul Bara,

Situated Language and Embodied Dialogue (SLED) Research Group 14 Dec 29, 2022
Neurons Dataset API - The official dataloader and visualization tools for Neurons Datasets.

Neurons Dataset API - The official dataloader and visualization tools for Neurons Datasets. Introduction We propose our dataloader API for loading and

1 Nov 19, 2021
GPOEO is a micro-intrusive GPU online energy optimization framework for iterative applications

GPOEO GPOEO is a micro-intrusive GPU online energy optimization framework for iterative applications. We also implement ODPP [1] as a comparison. [1]

瑞雪轻飏 8 Sep 10, 2022