Dota 2

11 papers with code • 0 benchmarks • 0 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 )

Most implemented papers

Proximal Policy Optimization Algorithms

labmlai/annotated_deep_learning_paper_implementations 20 Jul 2017

We propose 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.

An Empirical Model of Large-Batch Training

astooke/rlpyt 14 Dec 2018

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency.

Multi-Agent Collaboration via Reward Attribution Decomposition

facebookresearch/CollaQ 16 Oct 2020

In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.

Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analytics

chitaapc/dota2ccr 29 May 2023

Therefore, the proposed methodology for representing characters can increase the life-spam of machine learning models as well as contribute to a higher performance when compared to traditional techniques typically employed within the literature.

Real-time eSports Match Result Prediction

yang1fan2/Dota2-Prediction 10 Dec 2016

In this paper, we try to predict the winning team of a match in the multiplayer eSports game Dota 2.

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

adam-katona/dota2_death_prediction 21 May 2019

Even though death events are rare within a game (1\% of the data), the model achieves 0. 377 precision with 0. 725 recall on test data when prompted to predict which of any of the 10 players of either team will die within 5 seconds.

Dota 2 with Large Scale Deep Reinforcement Learning

bilibili/LastOrder-Dota2 13 Dec 2019

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.

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

tencent-ailab/tleague_projpage 25 Nov 2020

This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems.

Machine learning models for DOTA 2 outcomes prediction

KodirjonAkhmedov/Real-Time-Data-Collection-Dota-2 3 Jun 2021

Prediction of the real-time multiplayer online battle arena (MOBA) games' match outcome is one of the most important and exciting tasks in Esports analytical research.

Joint action loss for proximal policy optimization

ubiquition/drl 26 Jan 2023

Instead, for each sub-action we calculate the loss separately, which is less prone to clipping during updates thereby making better use of samples.