Papers with Code 아카이브
Starcraft II
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 3
Starcraft II is a RTS game; the task is to train an agent to play the game.
<span style="color:grey; opacity: 0.6">( Image credit: The StarCraft Multi-Agent Challenge )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
RODE: Learning Roles to Decompose Multi-Agent Tasks
Energy-based Surprise Minimization for Multi-Agent Value Factorization
BGC: Multi-Agent Group Belief with Graph Clustering
Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection
QPLEX: Duplex Dueling Multi-Agent Q-Learning
Value-Decomposition Multi-Agent Actor-Critics
Off-Policy Multi-Agent Decomposed Policy Gradients
S2RMs: Spatially Structured Recurrent Modules
Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
StarCraft II Build Order Optimization using Deep Reinforcement Learning and Monte-Carlo Tree Search
Incorporating Pragmatic Reasoning Communication into Emergent Language
Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization
Real World Games Look Like Spinning Tops
F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning
FACMAC: Factored Multi-Agent Centralised Policy Gradients
A Limited-Capacity Minimax Theorem for Non-Convex Games or: How I Learned to Stop Worrying about Mixed-Nash and Love Neural Nets
Heterogeneous Learning from Demonstration
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
A Narration-based Reward Shaping Approach using Grounded Natural Language Commands
Deep Coordination Graphs
Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
Action Semantics Network: Considering the Effects of Actions in Multiagent Systems
Arena: a toolkit for Multi-Agent Reinforcement Learning
Learning a Behavioral Repertoire from Demonstrations
Explainable Reinforcement Learning Through a Causal Lens
Grounding Natural Language Commands to StarCraft II Game States for Narration-Guided Reinforcement Learning
Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.