A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm

Last update: Dec 28, 2022

Overview

Multi-Agent-Deep-Deterministic-Policy-Gradients

A Pytorch implementation of the multi agent deep deterministic policy gradients(MADDPG) algorithm

This is my implementation of the algorithm presented in the paper: Multi Agent Actor Critic for Mixed Cooperative-Competitive Environments. You can find this paper here: https://arxiv.org/pdf/1706.02275.pdf

You will need to install the Multi Agent Particle Environment(MAPE), which you can find here: https://github.com/openai/multiagent-particle-envs

Make sure to create a virtual environment with the dependencies for the MAPE, since they are somewhat out of date. I also recommend running this with PyTorch version 1.4.0, as the latest version (1.8) seems to have an issue with an in place operation I use in the calculation of the critic loss.

It's probably easiest to just clone this repo into the same directory as the MAPE, as the main file requires the make_env function from that package.

The video for this tutorial is found here: https://youtu.be/tZTQ6S9PfkE

A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm

Related tags

Overview

Multi-Agent-Deep-Deterministic-Policy-Gradients

Owner

Phil Tabor

TorchIO is a Medical image preprocessing and augmentation toolkit for deep learning. Part of the PyTorch Ecosystem.

Introduction to Statistics and Basics of Mathematics for Data Science - The Hacker's Way

Using modified BiSeNet for face parsing in PyTorch

Code for ACL'2021 paper WARP 🌀 Word-level Adversarial ReProgramming

MultiLexNorm 2021 competition system from ÚFAL

Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI

Open source code for the paper of Neural Sparse Voxel Fields.

kapre: Keras Audio Preprocessors

Riemannian Convex Potential Maps

Official implementation of ACMMM'20 paper 'Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework'

VSR-Transformer - This paper proposes a new Transformer for video super-resolution (called VSR-Transformer).

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

Out-of-Town Recommendation with Travel Intention Modeling (AAAI2021)

An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates neural fields, predictive coding, top-down-bottom-up, and attention (consensus between columns)

A Robust Unsupervised Ensemble of Feature-Based Explanations using Restricted Boltzmann Machines

Rank1 Conversation Emotion Detection Task

The first dataset of composite images with rationality score indicating whether the object placement in a composite image is reasonable.

This is the official pytorch implementation for the paper: Instance Similarity Learning for Unsupervised Feature Representation.

Official implementation for Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

Code for paper entitled "Improving Novelty Detection using the Reconstructions of Nearest Neighbours"