Starcraft II
3개 벤치마크 · 논문 196편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
The StarCraft Multi-Agent Challenge
The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
StarCraft II: A New Challenge for Reinforcement Learning
Perceiver IO: A General Architecture for Structured Inputs & Outputs
Relational Deep Reinforcement Learning
Papers
SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
Cooperative multi-agent reinforcement learning (MARL) faces significant challenges in maintaining robust coordination under noisy observations. Although observation disturbances are often introduced independently across …
Multi-agent Reinforcement LearningStarcraft IICCKS: Consensus-based Communication and Knowledge Sharing
In Decentralized Training and Decentralized Execution (DTDE) for cooperative Multi-Agent Reinforcement Learning (MARL), action-advising-based knowledge sharing promotes interpretable and scalable cooperation among agents…
Multi-agent Reinforcement LearningContrastive LearningStarcraft IIBridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus
Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decom…
Multi-agent Reinforcement LearningDecision MakingStarcraft IIOn Emotion-Sensitive Decision Making of Small Language Model Agents
Small language models (SLM) are increasingly used as interactive decision-making agents, yet most decision-oriented evaluations ignore emotion as a causal factor influencing behavior. We study emotion-sensitive decision …
Decision MakingStarcraft IIBreakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning
Value factorization, a popular paradigm in MARL, faces significant theoretical and algorithmic bottlenecks: its tendency to converge to suboptimal solutions remains poorly understood and unsolved. Theoretically, existing…
Multi-agent Reinforcement LearningStarcraft IIGRASP: Gradient Realignment via Active Shared Perception for Multi-Agent Collaborative Optimization
Non-stationarity arises from concurrent policy updates and leads to persistent environmental fluctuations. Existing approaches like Centralized Training with Decentralized Execution (CTDE) and sequential update schemes m…
Starcraft II