Papers with Code 아카이브
SMAC
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 101
The StarCraft Multi-Agent Challenge (SMAC) is a benchmark that provides elements of partial observability, challenging dynamics, and high-dimensional observation spaces. SMAC is built using the StarCraft II game engine, creating a testbed for research in cooperative MARL where each game unit is an independent RL agent.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning
Ensemble-MIX: Enhancing Sample Efficiency in Multi-Agent RL Using Ensemble Methods
Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning
POCAII: Parameter Optimization with Conscious Allocation using Iterative Intelligence
JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes
Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Delayed Observation
Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation
AVA: Attentive VLM Agent for Mastering StarCraft II
Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning
An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks
Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer
O-MAPL: Offline Multi-agent Preference Learning
BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC
LLM-PySC2: Starcraft II learning environment for Large Language Models
Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration
A New Approach to Solving SMAC Task: Generating Decision Tree Code from Large Language Models
A Safety Modulator Actor-Critic Method in Model-Free Safe Reinforcement Learning and Application in UAV Hovering
Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration
A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning
Improving Global Parameter-sharing in Physically Heterogeneous Multi-agent Reinforcement Learning with Unified Action Space
QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition
CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
Soft-QMIX: Integrating Maximum Entropy For Monotonic Value Function Factorization
Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
Efficient Multi-agent Reinforcement Learning by Planning
Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning
Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration
Better Understandings and Configurations in MaxSAT Local Search Solvers via Anytime Performance Analysis
PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.