NeurIPS-2021: Neural Auto-Curricula in Two-Player Zero-Sum Games.

Xidong Feng

Last update: Nov 11, 2022

Related tags

Deep Learning NAC

Overview

NAC

Official PyTorch implementation of NAC from the paper:

Neural Auto-Curricula in Two-Player Zero-Sum Games.

We release code for: Gradient based oracle(Game of skills/2d-rps), Implicit gradient(2d-rps), RL(IMP) and ES based training for Kuhn-poker.

How to run

We set our hyperparameters in the python file so you just need to run model_train.py in the corresponding directory. We also offer our pretrain model for direct test.

We use wandb to log experimental results, you may need to register for an account before running the code.

How to test

Run test.py and you can check the comment in test.py for different test configurations.

2D-RPS visualization

Visualisation results can be tested in:

2d-rps-gradient/visualisation/visualization_2d_rps.ipynb.

Kuhn->Leduc Generalization

we provide a local implementation in which one can reproduce the results of generalising our models trained on Kuhn Poker to Leduc Poker.

cd leduc_poker
# To reproduce the approximate best-response results
python3 kuhn_to_leduc.py --br_type 'approx_br_rand'
# To reproduce the exact best-response results
python3 kuhn_to_leduc.py --br_type 'exact_br'

Cite

Please cite our paper if you use the code or datasets in your own work:

@article{feng2021NAC,
  title={Neural Auto-Curricula},
  author={Feng, Xidong and Slumbers, Oliver and Yang, Yaodong and Wan, Ziyu and Liu, Bo and McAleer, Stephen and Wen, Ying and Wang, Jun},
  journal={arXiv preprint arXiv:2106.02745},
  year={2021}
}

GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks

GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks This repository implements a capsule model Inten

15 Dec 24, 2022

Projects for AI/ML and IoT integration for games and other presented at re:Invent 2021.

Playground4AWS Projects for AI/ML and IoT integration for games and other presented at re:Invent 2021. Architecture Minecraft and Lamps This project i

5 Nov 30, 2022

Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Code To run: python runner.py new --save SAVE_NAME --data PATH_TO_DATA_DIR --dataset DATASET --model model_name [options] --n 1000 - train - t

5 Dec 12, 2022

This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).

NeurIPS 2021 (Spotlight): Task-Adaptive Neural Network Search with Meta-Contrastive Learning This is an official PyTorch implementation of Task-Adapti

15 Nov 21, 2022

Source code of NeurIPS 2021 Paper ''Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration''

CaGCN This repo is for source code of NeurIPS 2021 paper "Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration". Paper L

6 Dec 19, 2022

Code repo for "RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network" (Machine Learning and the Physical Sciences workshop in NeurIPS 2021).

RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network An official PyTorch implementation of the RBSRICNN network as desc

6 Nov 14, 2022

Comments

Maybe a bug in visualisation utils

https://github.com/waterhorse1/NAC/blob/dd355a9d53909470c7e26fb8a7ee7380ea2bb02a/2d-rps-gradient/visualisation/utils/best_responder.py#L104 I didn't deep into the code, but maybe a bug ? mus -> mu ?

opened by hejujie 3

NeurIPS-2021: Neural Auto-Curricula in Two-Player Zero-Sum Games.

Related tags

Overview

NAC

How to run

How to test

2D-RPS visualization

Kuhn->Leduc Generalization

Cite

You might also like...

GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks

Projects for AI/ML and IoT integration for games and other presented at re:Invent 2021.

Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).

Source code of NeurIPS 2021 Paper ''Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration''

Code repo for "RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network" (Machine Learning and the Physical Sciences workshop in NeurIPS 2021).

Official implementation of Neural Bellman-Ford Networks (NeurIPS 2021)

[CVPR 2021] Released code for Counterfactual Zero-Shot and Open-Set Visual Recognition

Zero-shot Synthesis with Group-Supervised Learning (ICLR 2021 paper)

Comments

Maybe a bug in visualisation utils

Owner

Xidong Feng

Code for Two-stage Identifier: "Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition"

Code for our NeurIPS 2021 paper Mining the Benefits of Two-stage and One-stage HOI Detection

Implements an infinite sum of poisson-weighted convolutions

Sum-Product Probabilistic Language

Consecutive-Subsequence - Simple software to calculate susequence with highest sum

Multiple-criteria decision-making (MCDM) with Electre, Promethee, Weighted Sum and Pareto

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

Official implementation for Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder at NeurIPS 2020

Neural network chess engine trained on Gary Kasparov's games.

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).