Rainbow DQN implementation that outperforms the paper's results on 40% of games using 20x less data 🌈

Overview

Rainbow 🌈

An implementation of Rainbow DQN which outperforms the paper's (Hessel et al. 2017) results on 40% of tested games while using 20x less data. This was developed as part of an undergraduate university course on scientific research and writing. The results are also available as a spreadsheet here. A selection of videos is available here.

Key Changes and Results

  • We implemented the large IMPALA CNN with 2x channels from Espeholt et al. (2018).
  • The implementation uses large, vectorized environments, asynchronous environment interaction, mixed-precision training, and larger batch sizes to reduce training time.
  • Integrations and recommended preprocessing for >1000 environments from gym, gym-retro and procgen are provided.
  • Due to compute and time constraints, we only trained for 10M frames (compared to 200M in the paper).
  • We implemented all components apart from distributional RL (we saw mixed results with C51 and QR-DQN).

When trained for only 10M frames, this implementation outperforms:

google/dopamine trained for 10M frames on 96% of games
google/dopamine trained for 200M frames on 64% of games
Hessel, et al. (2017) trained for 200M frames on 40% of games
Human results on 72% of games

Most of the observed performance improvements compared to the paper come from switching to the IMPALA CNN as well as some hyperparameter changes (e.g. the 4x larger learning rate).

Setup

Install necessary prerequisites with

sudo apt install zlib1g-dev cmake unrar
pip install wandb gym[atari]==0.18.0 imageio moviepy torchsummary tqdm rich procgen gym-retro torch stable_baselines3 atari_py==0.2.9

If you intend to use gym Atari games, you will need to install these separately, e.g., by running:

wget http://www.atarimania.com/roms/Roms.rar 
unrar x Roms.rar
python -m atari_py.import_roms .

To set up gym-retro games you should follow the instructions here.

How to use

To get started right away, run

python train_rainbow.py --env_name gym:Qbert

This will train Rainbow on Atari Qbert and log all results to "Weights and Biases" and the checkpoints directory.

Please take a look at common/argp.py or run python train_rainbow.py --help for more configuration options.

Some Notes

  • With a single RTX 2080 and 12 CPU cores, training for 10M frames takes around 8-12 hours, depending on the used settings
  • About 15GB of RAM are required. When using a larger replay buffer or subprocess envs, memory use may be much higher
  • Hyperparameters can be configured through command line arguments; defaults can be found in common/argp.py
  • For fastest training throughput use batch_size=512, parallel_envs=64, train_count=1, subproc_vecenv=True

Acknowledgements

We are very grateful to the TU Wien DataLab for providing the majority of the compute resources that were necessary to perform the experiments.

Here are some other implementations and resources that were helpful in the completion of this project:

Owner
Dominik Schmidt
I'm a computer science & math student at the Vienna University of Technology in Austria.
Dominik Schmidt
OneShot Learning-based hotword detection.

EfficientWord-Net Hotword detection based on one-shot learning Home assistants require special phrases called hotwords to get activated (eg:"ok google

ANT-BRaiN 102 Dec 25, 2022
Implementation of GGB color space

GGB Color Space This package is implementation of GGB color space from Development of a Robust Algorithm for Detection of Nuclei and Classification of

Resha Dwika Hefni Al-Fahsi 2 Oct 06, 2021
Jiminy Cricket Environment (NeurIPS 2021)

Jiminy Cricket This is the repository for "What Would Jiminy Cricket Do? Towards Agents That Behave Morally" by Dan Hendrycks*, Mantas Mazeika*, Andy

Dan Hendrycks 15 Aug 29, 2022
This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

A Memory-saving Training Framework for Transformers This is the official PyTorch implementation for Mesa: A Memory-saving Training Framework for Trans

Zhuang AI Group 105 Dec 06, 2022
Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking.

DEFT: Detection Embeddings for Tracking DEFT: Detection Embeddings for Tracking, Mohamed Chaabane, Peter Zhang, J. Ross Beveridge, Stephen O'Hara

Mohamed Chaabane 253 Dec 18, 2022
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

SVHNClassifier-PyTorch A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks If

Potter Hsu 182 Jan 03, 2023
It is a system used to detect bone fractures. using techniques deep learning and image processing

MohammedHussiengadalla-Intelligent-Classification-System-for-Bone-Fractures It is a system used to detect bone fractures. using techniques deep learni

Mohammed Hussien 7 Nov 11, 2022
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID,

Intermediate Domain Module (IDM) This repository is the official implementation for IDM: An Intermediate Domain Module for Domain Adaptive Person Re-I

Yongxing Dai 87 Nov 22, 2022
This repo is customed for VisDrone.

Object Detection for VisDrone(无人机航拍图像目标检测) My environment 1、Windows10 (Linux available) 2、tensorflow = 1.12.0 3、python3.6 (anaconda) 4、cv2 5、ensemble

53 Jul 17, 2022
Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

NeX: Real-time View Synthesis with Neural Basis Expansion Project Page | Video | Paper | COLAB | Shiny Dataset We present NeX, a new approach to novel

538 Jan 09, 2023
JAX bindings to the Flatiron Institute Non-uniform Fast Fourier Transform (FINUFFT) library

JAX bindings to FINUFFT This package provides a JAX interface to (a subset of) the Flatiron Institute Non-uniform Fast Fourier Transform (FINUFFT) lib

Dan Foreman-Mackey 32 Oct 15, 2022
[CVPR 2021] Generative Hierarchical Features from Synthesizing Images

[CVPR 2021] Generative Hierarchical Features from Synthesizing Images

GenForce: May Generative Force Be with You 148 Dec 09, 2022
Final Project for the CS238: Decision Making Under Uncertainty course at Stanford University in Autumn '21.

Final Project for the CS238: Decision Making Under Uncertainty course at Stanford University in Autumn '21. We optimized wind turbine placement in a wind farm, subject to wake effects, using Q-learni

Manasi Sharma 2 Sep 27, 2022
[CVPR 2022] Official PyTorch Implementation for "Reference-based Video Super-Resolution Using Multi-Camera Video Triplets"

Reference-based Video Super-Resolution (RefVSR) Official PyTorch Implementation of the CVPR 2022 Paper Project | arXiv | RealMCVSR Dataset This repo c

Junyong Lee 151 Dec 30, 2022
Relative Uncertainty Learning for Facial Expression Recognition

Relative Uncertainty Learning for Facial Expression Recognition The official implementation of the following paper at NeurIPS2021: Title: Relative Unc

35 Dec 28, 2022
Equivariant Imaging: Learning Beyond the Range Space

Equivariant Imaging: Learning Beyond the Range Space Equivariant Imaging: Learning Beyond the Range Space Dongdong Chen, Julián Tachella, Mike E. Davi

Dongdong Chen 46 Jan 01, 2023
The code for our CVPR paper PISE: Person Image Synthesis and Editing with Decoupled GAN, Project Page, supp.

PISE The code for our CVPR paper PISE: Person Image Synthesis and Editing with Decoupled GAN, Project Page, supp. Requirement conda create -n pise pyt

jinszhang 110 Nov 21, 2022
Code of Puregaze: Purifying gaze feature for generalizable gaze estimation, AAAI 2022.

PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation Description Our work is accpeted by AAAI 2022. Picture: We propose a domain-general

39 Dec 05, 2022
List some popular DeepFake models e.g. DeepFake, FaceSwap-MarekKowal, IPGAN, FaceShifter, FaceSwap-Nirkin, FSGAN, SimSwap, CihaNet, etc.

deepfake-models List some popular DeepFake models e.g. DeepFake, CihaNet, SimSwap, FaceSwap-MarekKowal, IPGAN, FaceShifter, FaceSwap-Nirkin, FSGAN, Si

Mingcan Xiang 100 Dec 17, 2022
Instance-based label smoothing for improving deep neural networks generalization and calibration

Instance-based Label Smoothing for Neural Networks Pytorch Implementation of the algorithm. This repository includes a new proposed method for instanc

Mohamed Maher 1 Aug 13, 2022