Evaluating different engineering tricks that make RL work

Overview

Reinforcement Learning Tricks, Index

This repository contains the code for the paper "Distilling Reinforcement Learning Tricks for Video Games".

Short story shorter: RL algorithms are neat and all, but to get it to work in video games (RL competitions and whatnot), there are some nifty little tricks involved that need bit of expertise in the domain. This includes reward shaping, curriculum learning, splitting task into subtasks by hand and guiding agent's actions. We took some of these tricks and tried them on three environments with DQN. With right setup you get more out of DQN.

Code authors: Anssi Kanervisto, Christian Scheller and Yanick Schraner.

The experiments in the three environments are split into three git branches:

  • vizdoom for ViZDoom Deathmatch experiments
  • minerl for MineRL ObtainDiamond experiments
  • gfootball for Football environment experiments

To run the experiments, checkout the repository you want to run experiments for with git checkout [branch name], and follow the instructions in the README file there.

After running all the experiments, collect the results as described the respective branches. You should have three directories

  • vizdoom-runs
  • minerl-runs
  • football-runs

After this, running python plot_paper.py should create a figures/learning_curves.pdf file which summarizes the results.

Owner
Anssi
PhD student at the University of Eastern Finland. In search of ways for beating humans in various video games. Some speech processing as a side dish.
Anssi
This repository contains project created during the Data Challenge module at London School of Hygiene & Tropical Medicine

LSHTM_RCS This repository contains project created during the Data Challenge module at London School of Hygiene & Tropical Medicine (LSHTM) in collabo

Lukas Kopecky 3 Jan 30, 2022
Generative vs Discriminative: Rethinking The Meta-Continual Learning (NeurIPS 2021)

Generative vs Discriminative: Rethinking The Meta-Continual Learning (NeurIPS 2021) In this repository we provide PyTorch implementations for GeMCL; a

4 Apr 15, 2022
MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving

MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving Code will be available soon. Motivation Architecture

Kai Chen 24 Apr 19, 2022
Official PyTorch implementation of "Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics".

Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics This repository is the official PyTorch implementation of "Physics-aware Differ

USC-Melady 46 Nov 20, 2022
Python package to add text to images, textures and different backgrounds

nider Python package for text images generation and watermarking Free software: MIT license Documentation: https://nider.readthedocs.io. nider is an a

Vladyslav Ovchynnykov 131 Dec 30, 2022
VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

Preparation Please see dataset/README.md to get more details about our datasets-VIL100 Please see INSTALL.md to install environment and evaluation too

82 Dec 15, 2022
DEMix Layers for Modular Language Modeling

DEMix This repository contains modeling utilities for "DEMix Layers: Disentangling Domains for Modular Language Modeling" (Gururangan et. al, 2021). T

Suchin 43 Nov 11, 2022
Code for Efficient Visual Pretraining with Contrastive Detection

Code for DetCon This repository contains code for the ICCV 2021 paper "Efficient Visual Pretraining with Contrastive Detection" by Olivier J. Hénaff,

DeepMind 56 Nov 13, 2022
Implementation for the paper 'YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs'

YOLO-ReT This is the original implementation of the paper: YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs. Prakhar Ganesh, Ya

69 Oct 19, 2022
Simulation-based performance analysis of server-less Blockchain-enabled Federated Learning

Blockchain-enabled Server-less Federated Learning Repository containing the files used to reproduce the results of the publication "Blockchain-enabled

Francesc Wilhelmi 9 Sep 27, 2022
✨风纪委员会自动投票脚本,利用Github Action帮你进行裁决操作(为了让其他风纪委员有案件可判,本程序从中午12点才开始运行,有需要请自己修改运行时间)

风纪委员会自动投票 本脚本通过使用Github Action来实现B站风纪委员的自动投票功能,喜欢请给我点个STAR吧! 如果你不是风纪委员,在符合风纪委员申请条件的情况下,本脚本会自动帮你申请 投票时间是早上八点,如果有需要请自行修改.github/workflows/Judge.yml中的时间,

Pesy Wu 25 Feb 17, 2021
Highway networks implemented in PyTorch.

PyTorch Highway Networks Highway networks implemented in PyTorch. Just the MNIST example from PyTorch hacked to work with Highway layers. Todo Make th

Conner Vercellino 56 Dec 14, 2022
Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"

GAN stability This repository contains the experiments in the supplementary material for the paper Which Training Methods for GANs do actually Converg

Lars Mescheder 885 Jan 01, 2023
AquaTimer - Programmable Timer for Aquariums based on ATtiny414/814/1614

AquaTimer - Programmable Timer for Aquariums based on ATtiny414/814/1614 AquaTimer is a programmable timer for 12V devices such as lighting, solenoid

Stefan Wagner 4 Jun 13, 2022
The sixth place winning solution (6/220) in 2021 Gaofen Challenge.

SwinTransformer + OBBDet The sixth place winning solution (6/220) in the track of Fine-grained Object Recognition in High-Resolution Optical Images, 2

ming71 46 Dec 02, 2022
HyperaPy: An automatic hyperparameter optimization framework ⚡🚀

hyperpy HyperPy: An automatic hyperparameter optimization framework Description HyperPy: Library for automatic hyperparameter optimization. Build on t

Sergio Mora 7 Sep 06, 2022
Code repository for Semantic Terrain Classification for Off-Road Autonomous Driving

BEVNet Datasets Datasets should be put inside data/. For example, data/semantic_kitti_4class_100x100. Training BEVNet-S Example: cd experiments bash t

(Brian) JoonHo Lee 24 Dec 12, 2022
OneFlow is a performance-centered and open-source deep learning framework.

OneFlow OneFlow is a performance-centered and open-source deep learning framework. Latest News Version 0.5.0 is out! First class support for eager exe

OneFlow 4.2k Jan 07, 2023
Multi-Person Extreme Motion Prediction

Multi-Person Extreme Motion Prediction Implementation for paper Wen Guo, Xiaoyu Bie, Xavier Alameda-Pineda, Francesc Moreno-Noguer, Multi-Person Extre

GUO-W 38 Nov 15, 2022
🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series

🌾 PASTIS 🌾 Panoptic Agricultural Satellite TIme Series (optical and radar) The PASTIS Dataset Dataset presentation PASTIS is a benchmark dataset for

86 Jan 04, 2023