paper-with-me

SMAC 벤치마크

SMAC on SMAC 6h_vs_8z

28개 결과 · ⬇ CSV · JSON

Median Win Rate

0 23.44 46.88 70.31 93.75 2019-02 2026-09 QMIX — 3.0 (2019-02-11) IQL — 0.0 (2019-02-11) VDN — 0.0 (2019-02-11) Heuristic — 0.0 (2019-02-11) QMIX — 3.0 (2019-02-11) IQL — 0.0 (2019-02-11) VDN — 0.0 (2019-02-11) Heuristic — 0.0 (2019-02-11) QMIX — 3.0 (2020-03-19) QMIX — 3.0 (2020-03-19) DDN — 83.92 (2021-02-16) DMIX — 49.43 (2021-02-16) QMIX — 12.78 (2021-02-16) VDN — 0.0 (2021-02-16) DIQL — 0.0 (2021-02-16) IQL — 0.0 (2021-02-16) DDN — 83.92 (2021-02-16) DMIX — 49.43 (2021-02-16) QMIX — 12.78 (2021-02-16) VDN — 0.0 (2021-02-16) DIQL — 0.0 (2021-02-16) IQL — 0.0 (2021-02-16) ACE — 93.75 (2022-11-29) ACE — 93.75 (2022-11-29) DPLEX — 43.75 (2023-06-04) DPLEX — 43.75 (2023-06-04) QMIX — 3.0 (2019-02-11) DDN — 83.92 (2021-02-16) ACE — 93.75 (2022-11-29)
RankModel Median Win RateAverage Score PaperCodeYear
1 ACE 93.75– ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency opendilab/ace 2022
2 DDN 83.9219.4 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
3 DMIX 49.4317.14 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
4 DPLEX 43.7517.88 A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning j3soon/dfac-extended 2023
5 QMIX 12.7814.37 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
6 QMIX 3– The StarCraft Multi-Agent Challenge oxwhirl/pymarl · starry-sky6688/marl-algorithms · oxwhirl/smac · +20 2019
6 QMIX 3– Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning oxwhirl/pymarl 2020
8 VDN 015.41 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
8 DIQL 0.0014.94 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
8 IQL 013.78 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
8 IQL 0– The StarCraft Multi-Agent Challenge oxwhirl/pymarl · starry-sky6688/marl-algorithms · oxwhirl/smac · +20 2019
8 VDN 0– The StarCraft Multi-Agent Challenge oxwhirl/pymarl · starry-sky6688/marl-algorithms · oxwhirl/smac · +20 2019
8 Heuristic 0– The StarCraft Multi-Agent Challenge oxwhirl/pymarl · starry-sky6688/marl-algorithms · oxwhirl/smac · +20 2019
14 QPLEX –15.95 A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning j3soon/dfac-extended 2023
15 ACE 93.75– ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency opendilab/ace 2022
16 DDN 83.9219.4 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
17 DMIX 49.4317.14 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
18 DPLEX 43.7517.88 A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning j3soon/dfac-extended 2023
19 QMIX 12.7814.37 DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning j3soon/dfac 2021
20 QMIX 3– The StarCraft Multi-Agent Challenge oxwhirl/pymarl · starry-sky6688/marl-algorithms · oxwhirl/smac · +20 2019
1–20 / 28 다음 → 페이지당 10 20 50 100