paper-with-me

Continuous Control 벤치마크

Continuous Control on PyBullet Ant

24개 결과 · ⬇ CSV · JSON

Return

1967 2340 2713 3086 3459 2020-05 2026-09 SAC gSDE — 3459.0 (2020-05-12) TD3 gSDE — 3267.0 (2020-05-12) TD3 — 2865.0 (2020-05-12) SAC — 2859.0 (2020-05-12) PPO gSDE — 2587.0 (2020-05-12) A2C gSDE — 2560.0 (2020-05-12) PPO — 2160.0 (2020-05-12) A2C — 1967.0 (2020-05-12) SAC gSDE — 3459.0 (2020-05-12) TD3 gSDE — 3267.0 (2020-05-12) TD3 — 2865.0 (2020-05-12) SAC — 2859.0 (2020-05-12) PPO gSDE — 2587.0 (2020-05-12) A2C gSDE — 2560.0 (2020-05-12) PPO — 2160.0 (2020-05-12) A2C — 1967.0 (2020-05-12) SAC gSDE — 3459.0 (2020-05-12) TD3 gSDE — 3267.0 (2020-05-12) TD3 — 2865.0 (2020-05-12) SAC — 2859.0 (2020-05-12) PPO gSDE — 2587.0 (2020-05-12) A2C gSDE — 2560.0 (2020-05-12) PPO — 2160.0 (2020-05-12) A2C — 1967.0 (2020-05-12) SAC gSDE — 3459.0 (2020-05-12)
RankModel Return PaperCodeYear
21 PPO gSDE 2587 Smooth Exploration for Robotic Reinforcement Learning DLR-RM/stable-baselines3 · facebookresearch/rl · araffin/sbx · +1 2020
22 A2C gSDE 2560 Smooth Exploration for Robotic Reinforcement Learning DLR-RM/stable-baselines3 · facebookresearch/rl · araffin/sbx · +1 2020
23 PPO 2160 Smooth Exploration for Robotic Reinforcement Learning DLR-RM/stable-baselines3 · facebookresearch/rl · araffin/sbx · +1 2020
24 A2C 1967 Smooth Exploration for Robotic Reinforcement Learning DLR-RM/stable-baselines3 · facebookresearch/rl · araffin/sbx · +1 2020
← 이전 21–24 / 24 페이지당 10 20 50 100