Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

Dota 2 | State-of-the-Art

video-games

Dota 2

3260 papers • 126 benchmarks • 313 datasets

Dota 2 is a multiplayer online battle arena (MOBA). The task is to train one-or-more agents to play and win the game. ( Image credit: OpenAI Five )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-games

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find video-games models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Proximal Policy Optimization Algorithms

Alec Radford, Filip Wolski, John Schulman, Oleg Klimov, Prafulla Dhariwal•Wed Jul 19 2017

A new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent, are proposed.

24784

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

An Empirical Model of Large-Batch Training

Dario Amodei, Sam McCandlish, J. Kaplan, OpenAI Dota Team•Thu Dec 13 2018

It is demonstrated that a simple and easy-to-measure statistic called the gradient noise scale predicts the largest useful batch size across many domains and applications, including a number of supervised learning datasets, reinforcement learning domains, and even generative model training (autoencoders on SVHN).

362 0

Paper Graph

Real-time eSports Match Result Prediction

Tian Qin, Yulin Lei•Fri Dec 09 2016

This paper tries to predict the winning team of a match in the multiplayer eSports game Dota 2 by considering more aspects of prior (pre-match) features from individual players' match history, as well as real-time features at each minute as the match progresses.

50 0

Paper Graph

Dota 2 with Large Scale Deep Reinforcement Learning

I. Sutskever, Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemyslaw Debiak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Christopher Hesse, R. Józefowicz, Scott Gray, Catherine Olsson, J. Pachocki, Michael Petrov, Henrique Pondé de Oliveira Pinto, Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Jie Tang, Filip Wolski, Susan Zhang•Thu Dec 12 2019

By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.

2008 0

Paper Graph

TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning

Zhengyou Zhang, Jiechao Xiong, Peng Sun, Xinghai Sun, Lei Han, Shuxing Li, Jiawei Xu, Meng Fang•Tue Nov 24 2020

A framework, referred to as TLeague, that aims at large-scale training and implements several main-stream CSP-MARL algorithms, which achieves a high throughput and a reasonable scale-up when performing distributed training.

20 0

Paper Graph

Machine learning models for DOTA 2 outcomes prediction

Kodirjon Akhmedov, A. Phan•Wed Jun 02 2021

This research paper predominantly focuses on building predictive machine and deep learning models to identify the outcome of the Dota 2 MOBA game using the new method of multi-forward steps predictions.

17 0

Paper Graph

Time to Die: Death Prediction in Dota 2 using Deep Learning

Adam Katona, Ryan J. Spick, Victoria J. Hodge, Simon Demediuk, Florian Block, Anders Drachen, James Alfred Walker•Mon May 20 2019

A deep learning network with shared weights which provides accurate death predictions within a five-second window in Dota 2, one of the most played esports titles in the world, giving commentators and viewers time to move their attention to these key events.

42 0

Paper Graph

Multi-Agent Collaboration via Reward Attribution Decomposition

K. Keutzer, Joseph E. Gonzalez, Xiaolong Wang, Yuandong Tian, Huazhe Xu, Tianjun Zhang, Yi Wu•Thu Oct 15 2020

CollaQ is proposed, a Collaborative Q-learning that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play and outperforms previous SoTA by over 30%.

46 0

Paper Graph

Adding a benchmark result helps the community track progress.