SOTAVerified|Agents Browse Leaderboard About

Dota 2

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 )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 27 papers

Title	Date	Tasks	Status	Hype	Score
Proximal Policy Optimization Algorithms	Jul 20, 2017	Continuous ControlDota 2	CodeCode Available	2	5
An Empirical Model of Large-Batch Training	Dec 14, 2018	Dota 2model	CodeCode Available	2	5
Joint action loss for proximal policy optimization	Jan 26, 2023	Dota 2MuJoCo	CodeCode Available	1	5
Multi-Agent Collaboration via Reward Attribution Decomposition	Oct 16, 2020	Dota 2Multi-agent Reinforcement Learning	CodeCode Available	1	5
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning	Nov 25, 2020	Dota 2Multi-agent Reinforcement Learning	CodeCode Available	1	5
Machine learning models for DOTA 2 outcomes prediction	Jun 3, 2021	BIG-bench Machine LearningDota 2	CodeCode Available	1	5
Semantic HELM: A Human-Readable Memory for Reinforcement Learning	Jun 15, 2023	Dota 2Language Modelling	CodeCode Available	1	5
Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analytics	May 29, 2023	Dota 2Game Design	CodeCode Available	0	5
Dota 2 with Large Scale Deep Reinforcement Learning	Dec 13, 2019	Deep Reinforcement LearningDota 2	CodeCode Available	0	5
Real-time eSports Match Result Prediction	Dec 10, 2016	AttributeDota 2	CodeCode Available	0	5

Show:10 25 50

← PrevPage 1 of 3Next →

No leaderboard results yet.