Papers with Code 아카이브
Dota 2
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Dota 2 is a multiplayer online battle arena (MOBA). The task is to train one-or-more agents to play and win the game.
<span style="color:grey; opacity: 0.6">( Image credit: OpenAI Five )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
Towards Detecting Contextual Real-Time Toxicity for In-Game Chat
Semantic HELM: A Human-Readable Memory for Reinforcement Learning
Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analytics
Joint action loss for proximal policy optimization
Sequential Item Recommendation in the MOBA Game Dota 2
Maximum Entropy Model-based Reinforcement Learning
Learning Diverse Policies in MOBA Games via Macro-Goals
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection
Machine learning models for DOTA 2 outcomes prediction
The Dota 2 Bot Competition
Towards Playing Full MOBA Games with Deep Reinforcement Learning
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
Multi-Agent Collaboration via Reward Attribution Decomposition
Automatic Player Identification in Dota 2
Dota 2 with Large Scale Deep Reinforcement Learning
Neural Network Surgery with Sets
Long-Term Planning and Situational Awareness in OpenAI Five
Time to Die: Death Prediction in Dota 2 using Deep Learning
An Empirical Model of Large-Batch Training
Proximal Policy Optimization Algorithms
Real-time eSports Match Result Prediction
Real-Time Video Highlights for Yahoo Esports
Skill-Based Differences in Spatio-Temporal Team Behavior in Defence of The Ancients 2
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.