SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 27 papers

TitleStatusHype
An Empirical Model of Large-Batch TrainingCode2
Proximal Policy Optimization AlgorithmsCode2
Semantic HELM: A Human-Readable Memory for Reinforcement LearningCode1
Joint action loss for proximal policy optimizationCode1
Machine learning models for DOTA 2 outcomes predictionCode1
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement LearningCode1
Multi-Agent Collaboration via Reward Attribution DecompositionCode1
Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match MetadataCode0
Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks—0
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play—0
Towards Detecting Contextual Real-Time Toxicity for In-Game ChatCode0
Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport AnalyticsCode0
Sequential Item Recommendation in the MOBA Game Dota 2—0
Maximum Entropy Model-based Reinforcement Learning—0
Learning Diverse Policies in MOBA Games via Macro-Goals—0
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection—0
The Dota 2 Bot Competition—0
Factored Action Spaces in Deep Reinforcement Learning—0
Towards Playing Full MOBA Games with Deep Reinforcement Learning—0
Automatic Player Identification in Dota 2—0
Long-Term Planning and Situational Awareness in OpenAI Five—0
Dota 2 with Large Scale Deep Reinforcement LearningCode0
Neural Network Surgery with Sets—0
Time to Die: Death Prediction in Dota 2 using Deep LearningCode0
Real-time eSports Match Result PredictionCode0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.