World Models with TensorFlow 2

Overview

World Models

This repo reproduces the original implementation of World Models. This implementation uses TensorFlow 2.2.

Docker

The easiest way to handle dependencies is with Nvidia-Docker. Follow the instructions below to generate and attach to the container.

docker image build -t wm:1.0 -f docker/Dockerfile.wm .
docker container run -p 8888:8888 --gpus '"device=0"' --detach -it --name wm wm:1.0
docker attach wm

Visualizations

To visualize the environment from the agents perspective or generate synthetic observations use the visualizations jupyter notebook. It can be launched from your container with the following:

jupyter notebook --no-browser --port=8888 --ip=0.0.0.0 --allow-root
Real Frame Sample Reconstructed Real Frame Imagined Frame
alt-text-1 alt-text-2 alt-text-3
Ground Truth (CarRacing) Reconstructed
drawing drawing
Ground Truth Environment (DoomTakeCover) Dream Environment
drawing drawing

Reproducing Results From Scratch

These instructions assume a machine with a 64 core cpu and a gpu. If running in the cloud it will likely financially make more sense to run the extraction and controller processes on a cpu machine and the VAE, preprocessing, and RNN tasks on a GPU machine.

DoomTakeCover-v0

CAUTION The doom environment leaves some processes hanging around. In addition to running the doom experiments, the script kills processes including 'vizdoom' in the name (be careful with this if you are not running in a container). To reproduce results for DoomTakeCover-v0 run the following bash script.

bash launch_scripts/wm_doom.bash

CarRacing-v0

To reproduce results for CarRacing-v0 run the following bash script

bash launch_scripts/carracing.bash

Disclaimer

I have not run this for long enough(~45 days wall clock time) to verify that we produce the same results on CarRacing-v0 as the original implementation.

Average return curves comparing the original implementation and ours. The shaded area represents a standard deviation above and below the mean.

alt text

For simplicity, the Doom experiment implementation is slightly different than the original

  • We do not use weighted cross entropy loss for done predictions
  • We train the RNN with sequences that always begin at the start of an episode (as opposed to random subsequences)
  • We sample whether the agent dies (as opposed to a deterministic cut-off)
\tau Returns Dream Environment        Returns Actual Environment       
D. Ha Original 1.0 1145 +/- 690 868 +/- 511
Eager 1.0 1465 +/- 633 849 +/- 499
Owner
Zac Wellmer
Zac Wellmer
CoMoGAN: continuous model-guided image-to-image translation. CVPR 2021 oral.

CoMoGAN: Continuous Model-guided Image-to-Image Translation Official repository. Paper CoMoGAN: continuous model-guided image-to-image translation [ar

166 Dec 31, 2022
Implementation for Learning to Track with Object Permanence

Learning to Track with Object Permanence A video-based MOT approach capable of tracking through full occlusions: Learning to Track with Object Permane

Toyota Research Institute - Machine Learning 91 Jan 03, 2023
Distributional Sliced-Wasserstein distance code

Distributional Sliced Wasserstein distance This is a pytorch implementation of the paper "Distributional Sliced-Wasserstein and Applications to Genera

VinAI Research 39 Jan 01, 2023
Self-Supervised Image Denoising via Iterative Data Refinement

Self-Supervised Image Denoising via Iterative Data Refinement Yi Zhang1, Dasong Li1, Ka Lung Law2, Xiaogang Wang1, Hongwei Qin2, Hongsheng Li1 1CUHK-S

Zhang Yi 72 Jan 01, 2023
A full pipeline AutoML tool for tabular data

HyperGBM Doc | 中文 We Are Hiring! Dear folks,we are offering challenging opportunities located in Beijing for both professionals and students who are k

DataCanvas 240 Jan 03, 2023
yufan 81 Dec 08, 2022
Learning Chinese Character style with conditional GAN

zi2zi: Master Chinese Calligraphy with Conditional Adversarial Networks Introduction Learning eastern asian language typefaces with GAN. zi2zi(字到字, me

Yuchen Tian 2.2k Jan 02, 2023
Multispectral Object Detection with Yolov5

Multispectral-Object-Detection Intro Official Code for Cross-Modality Fusion Transformer for Multispectral Object Detection. Multispectral Object Dete

Richard Fang 121 Jan 01, 2023
This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.

Multimodal Deep Learning 🎆 🎆 🎆 Announcing the multimodal deep learning repository that contains implementation of various deep learning-based model

Deep Cognition and Language Research (DeCLaRe) Lab 398 Dec 30, 2022
Civsim is a basic civilisation simulation and modelling system built in Python 3.8.

Civsim Introduction Civsim is a basic civilisation simulation and modelling system built in Python 3.8. It requires the following packages: perlin_noi

17 Aug 08, 2022
Pydantic models for pywttr and aiopywttr.

Pydantic models for pywttr and aiopywttr.

Almaz 2 Dec 08, 2022
Learning Correspondence from the Cycle-consistency of Time (CVPR 2019)

TimeCycle Code for Learning Correspondence from the Cycle-consistency of Time (CVPR 2019, Oral). The code is developed based on the PyTorch framework,

Xiaolong Wang 706 Nov 29, 2022
An pytorch implementation of Masked Autoencoders Are Scalable Vision Learners

An pytorch implementation of Masked Autoencoders Are Scalable Vision Learners This is a coarse version for MAE, only make the pretrain model, the fine

FlyEgle 214 Dec 29, 2022
Face recognition with trained classifiers for detecting objects using OpenCV

Face_Detector Face recognition with trained classifiers for detecting objects using OpenCV Libraries required to be installed using pip Command: cv2 n

Chumui Tripura 0 Oct 31, 2021
This is the code repository implementing the paper "TreePartNet: Neural Decomposition of Point Clouds for 3D Tree Reconstruction".

TreePartNet This is the code repository implementing the paper "TreePartNet: Neural Decomposition of Point Clouds for 3D Tree Reconstruction". Depende

刘彦超 34 Nov 30, 2022
Pytorch implementation for the Temporal and Object Quantification Networks (TOQ-Nets).

TOQ-Nets-PyTorch-Release Pytorch implementation for the Temporal and Object Quantification Networks (TOQ-Nets). Temporal and Object Quantification Net

Zhezheng Luo 9 Jun 30, 2022
Official repository of "DeepMIH: Deep Invertible Network for Multiple Image Hiding", TPAMI 2022.

DeepMIH: Deep Invertible Network for Multiple Image Hiding (TPAMI 2022) This repo is the official code for DeepMIH: Deep Invertible Network for Multip

Junpeng Jing 67 Nov 22, 2022
Streamlit Tutorial (ex: stock price dashboard, cartoon-stylegan, vqgan-clip, stylemixing, styleclip, sefa)

Streamlit Tutorials Install pip install streamlit Run cd [directory] streamlit run app.py --server.address 0.0.0.0 --server.port [your port] # http:/

Jihye Back 30 Jan 06, 2023
Pytorch implementation of SELF-ATTENTIVE VAD, ICASSP 2021

SELF-ATTENTIVE VAD: CONTEXT-AWARE DETECTION OF VOICE FROM NOISE (ICASSP 2021) Pytorch implementation of SELF-ATTENTIVE VAD | Paper | Dataset Yong Rae

97 Dec 23, 2022
AFLFast (extends AFL with Power Schedules)

AFLFast Power schedules implemented by Marcel Böhme [email protected]

Marcel Böhme 380 Jan 03, 2023