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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/nkai-decision-team/llm-pysc2
공식 코드LLM-PySC2: Starcraft II learning environment for Large Language Models
https://github.com/openai/multiagent-particle-envs
공식 코드Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/opendilab/ace
공식 코드ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
https://github.com/osilab-kaist/smac_exp
공식 코드https://github.com/oxwhirl/pymarl
공식 코드QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
https://github.com/oxwhirl/smac
공식 코드https://github.com/oxwhirl/smacv2
공식 코드SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
https://github.com/puyuan1996/MARL
공식 코드Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning
https://github.com/reinholdm/offline-pre-trained-multi-agent-decision-transformer
공식 코드Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks
https://github.com/schroederdewitt/multiagent_mujoco
공식 코드https://github.com/sisl/DICG
공식 코드Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
https://github.com/uoe-agents/smaclite
공식 코드SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning
https://github.com/vcis-wangchenxu/mrdg
공식 코드https://github.com/zdhnarsil/stochastic-marginal-actor-critic
공식 코드Latent State Marginalization as a Low-cost Approach for Improving Exploration
https://github.com/zhang-shaowei/smmae
공식 코드https://github.com/zzq-bot/romance
공식 코드Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers
https://github.com/15534081591/QMIX
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
https://github.com/16444take/aope-sim
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
https://github.com/2023-MindSpore-1/ms-code-221/tree/main/qmix
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/Acciorocketships/pymarl2
Rethinking the Implementation Matters in Cooperative Multi-Agent Reinforcement Learning
https://github.com/Ah31/maddpg_pytorch
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/AleXander-Tsui/MPE
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/Chan1998/MAAC
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/Denys88/rl_games
https://github.com/EyaRhouma/collaboration-competition-MADDPG
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/JinTanda/MADDPG_env
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/JohannesAck/MATD3implementation
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/JohannesAck/tf2multiagentrl
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/LXYYY/multiagent-particle-envs
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/Louiii/ValueDecomposition
Value-Decomposition Networks For Cooperative Multi-Agent Learning
https://github.com/MLStruckmann/mutation-misery
On the Performance of Differential Evolution for Hyperparameter Tuning
https://github.com/MrDaubinet/collaboration-and-competition
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/NeuroCSUT/intentions
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
https://github.com/RL-WFU/multi_agent_attack
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.