Evolution Strategies in PyTorch

Overview

Evolution Strategies

This is a PyTorch implementation of Evolution Strategies.

Requirements

Python 3.5, PyTorch >= 0.2.0, numpy, gym, universe, cv2

What is this? (For non-ML people)

A large class of problems in AI can be described as "Markov Decision Processes," in which there is an agent taking actions in an environment, and receiving reward, with the goal being to maximize reward. This is a very general framework, which can be applied to many tasks, from learning how to play video games to robotic control. For the past few decades, most people used Reinforcement Learning -- that is, learning from trial and error -- to solve these problems. In particular, there was an extension of the backpropagation algorithm from Supervised Learning, called the Policy Gradient, which could train neural networks to solve these problems. Recently, OpenAI had shown that black-box optimization of neural network parameters (that is, not using the Policy Gradient or even Reinforcement Learning) can achieve similar results to state of the art Reinforcement Learning algorithms, and can be parallelized much more efficiently. This repo is an implementation of that black-box optimization algorithm.

Usage

There are two neural networks provided in model.py, a small neural network meant for simple tasks with discrete observations and actions, and a larger Convnet-LSTM meant for Atari games.

Run python3 main.py --help to see all of the options and hyperparameters available to you.

Typical usage would be:

python3 main.py --small-net --env-name CartPole-v1

which will run the small network on CartPole, printing performance on every training batch. Default hyperparameters should be able to solve CartPole fairly quickly.

python3 main.py --small-net --env-name CartPole-v1 --test --restore path_to_checkpoint

which will render the environment and the performance of the agent saved in the checkpoint. Checkpoints are saved once per gradient update in training, always overwriting the old file.

python3 main.py --env-name PongDeterministic-v4 --n 10 --lr 0.01 --useAdam

which will train on Pong and produce a learning curve similar to this one:

Learning curve

This graph was produced after approximately 24 hours of training on a 12-core computer. I would expect that a more thorough hyperparameter search, and more importantly a larger batch size, would allow the network to solve the environment.

Deviations from the paper

  • I have not yet tried virtual batch normalization, but instead use the selu nonlinearity, which serves the same purpose but at a significantly reduced computational overhead. ES appears to be training on Pong quite well even with relatively small batch sizes and selu.

  • I did not pass rewards between workers, but rather sent them all to one master worker which took a gradient step and sent the new models back to the workers. If you have more cores than your batch size, OpenAI's method is probably more efficient, but if your batch size is larger than the number of cores, I think my method would be better.

  • I do not adaptively change the max episode length as is recommended in the paper, although it is provided as an option. The reasoning being that doing so is most helpful when you are running many cores in parallel, whereas I was using at most 12. Moreover, capping the episode length can severely cripple the performance of the algorithm if reward is correlated with episode length, as we cannot learn from highly-performing perturbations until most of the workers catch up (and they might not for a long time).

Tips

  • If you increase the batch size, n, you should increase the learning rate as well.

  • Feel free to stop training when you see that the unperturbed model is consistently solving the environment, even if the perturbed models are not.

  • During training you probably want to look at the rank of the unperturbed model within the population of perturbed models. Ideally some perturbation is performing better than your unperturbed model (if this doesn't happen, you probably won't learn anything useful). This requires 1 extra rollout per gradient step, but as this rollout can be computed in parallel with the training rollouts, this does not add to training time. It does, however, give us access to one less CPU core.

  • Sigma is a tricky hyperparameter to get right -- higher values of sigma will correspond to less variance in the gradient estimate, but will be more biased. At the same time, sigma is controlling the variance of our perturbations, so if we need a more varied population, it should be increased. It might be possible to adaptively change sigma based on the rank of the unperturbed model mentioned in the tip above. I tried a few simple heuristics based on this and found no significant performance increase, but it might be possible to do this more intelligently.

  • I found, as OpenAI did in their paper, that performance on Atari increased as I increased the size of the neural net.

Your code is making my computer slow help

Short answer: decrease the batch size to the number of cores in your computer, and decrease the learning rate as well. This will most likely hurt the performance of the algorithm.

Long answer: If you want large batch sizes while also keeping the number of spawned threads down, I have provided an old version in the slow_version branch which allows you to do multiple rollouts per thread, per gradient step. This code is not supported, however, and it is not recommended that you use it.

Contributions

Please feel free to make Github issues or send pull requests.

License

MIT

Owner
Andrew Gambardella
Machine Learning DPhil (PhD) student at University of Oxford
Andrew Gambardella
Small utility to demangle Nim symbols in callgrind files

nim_callgrind A small utility to demangle Nim symbols from callgrind files. Usage Run your (Nim) program with something like this: valgrind --tool=cal

kraptor 3 Feb 15, 2022
[CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427

Balanced MSE Code for the paper: Balanced MSE for Imbalanced Visual Regression Jiawei Ren, Mingyuan Zhang, Cunjun Yu, Ziwei Liu CVPR 2022 (Oral) News

Jiawei Ren 267 Jan 01, 2023
Ivy is a templated deep learning framework which maximizes the portability of deep learning codebases.

Ivy is a templated deep learning framework which maximizes the portability of deep learning codebases. Ivy wraps the functional APIs of existing frameworks. Framework-agnostic functions, libraries an

Ivy 8.2k Jan 02, 2023
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context This Repository contains the code on AVA of our ACM MM 2021 paper: LSTC: Boosting

Tencent YouTu Research 9 Oct 11, 2022
Official PyTorch implementation of "Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets" (ICLR 2021)

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets This is the official PyTorch implementation for the paper Rapid Neural A

48 Dec 26, 2022
A Python framework for conversational search

Chatty Goose Multi-stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting Installation Ma

Castorini 36 Oct 23, 2022
yolov5 deepsort 行人 车辆 跟踪 检测 计数

yolov5 deepsort 行人 车辆 跟踪 检测 计数 实现了 出/入 分别计数。 默认是 南/北 方向检测,若要检测不同位置和方向,可在 main.py 文件第13行和21行,修改2个polygon的点。 默认检测类别:行人、自行车、小汽车、摩托车、公交车、卡车。 检测类别可在 detect

554 Dec 30, 2022
Selene is a Python library and command line interface for training deep neural networks from biological sequence data such as genomes.

Selene is a Python library and command line interface for training deep neural networks from biological sequence data such as genomes.

Troyanskaya Laboratory 323 Jan 01, 2023
Semantic Segmentation Architectures Implemented in PyTorch

pytorch-semseg Semantic Segmentation Algorithms Implemented in PyTorch This repository aims at mirroring popular semantic segmentation architectures i

Meet Shah 3.3k Dec 29, 2022
Prototype-based Incremental Few-Shot Semantic Segmentation

Prototype-based Incremental Few-Shot Semantic Segmentation Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata, Barbara Caputo -- BMVC 20

Fabio Cermelli 21 Dec 29, 2022
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

About PyTorch 1.2.0 Now the master branch supports PyTorch 1.2.0 by default. Due to the serious version problem (especially torch.utils.data.dataloade

Sanghyun Son 2.1k Jan 01, 2023
Benchmarks for Object Detection in Aerial Images

Benchmarks for Object Detection in Aerial Images

Jian Ding 691 Dec 30, 2022
A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK

Pytorch-MBNet A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK Training To train a new model, please ru

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

[Project] Equivariant Imaging: Learning Beyond the Range Space Project about the

Georges Le Bellier 3 Feb 06, 2022
Repositorio oficial del curso IIC2233 Programación Avanzada 🚀✨

IIC2233 - Programación Avanzada Evaluación Las evaluaciones serán efectuadas por medio de actividades prácticas en clases y tareas. Se calculará la no

IIC2233 @ UC 47 Sep 06, 2022
Paddle implementation for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

ProcrustEs-KGE Paddle implementation for Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis 🙈 A more detailed re

Lincedo Lab 4 Jun 09, 2021
PyTorch implementation of UNet++ (Nested U-Net).

PyTorch implementation of UNet++ (Nested U-Net) This repository contains code for a image segmentation model based on UNet++: A Nested U-Net Architect

4ui_iurz1 642 Jan 04, 2023
Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination

Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination Pratul P. Srinivasan, Ben Mildenhall, Matthew Tancik, Jonathan T. Barron,

Pratul Srinivasan 65 Dec 14, 2022
An experimental technique for efficiently exploring neural architectures.

SMASH: One-Shot Model Architecture Search through HyperNetworks An experimental technique for efficiently exploring neural architectures. This reposit

Andy Brock 478 Aug 04, 2022