paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Defender

42개 결과 · ⬇ CSV · JSON

Score

3.064e+04 2.712e+05 5.118e+05 7.524e+05 9.93e+05 2015-11 2026-09 Duel noop — 42214.0 (2015-11-20) Prior+Duel noop — 41324.5 (2015-11-20) Prior+Duel hs — 34415.0 (2015-11-20) Duel noop — 42214.0 (2015-11-20) Prior+Duel noop — 41324.5 (2015-11-20) Prior+Duel hs — 34415.0 (2015-11-20) Persistent AL — 32038.93 (2015-12-15) Advantage Learning — 30643.59 (2015-12-15) Persistent AL — 32038.93 (2015-12-15) Advantage Learning — 30643.59 (2015-12-15) Reactor 500M — 223025.0 (2017-04-15) Reactor 500M — 223025.0 (2017-04-15) NoisyNet-Dueling — 42253.0 (2017-06-30) NoisyNet-Dueling — 42253.0 (2017-06-30) QR-DQN-1 — 47887.0 (2017-10-27) QR-DQN-1 — 47887.0 (2017-10-27) IMPALA (deep) — 185203.0 (2018-02-05) IMPALA (deep) — 185203.0 (2018-02-05) Ape-X — 411943.5 (2018-03-02) Ape-X — 411943.5 (2018-03-02) CGP — 993010.0 (2018-06-14) IQN — 53537.0 (2018-06-14) CGP — 993010.0 (2018-06-14) IQN — 53537.0 (2018-06-14) R2D2 — 665792.0 (2019-05-01) R2D2 — 665792.0 (2019-05-01) MuZero — 839642.95 (2019-11-19) MuZero — 839642.95 (2019-11-19) Agent57 — 677642.78 (2020-03-30) Agent57 — 677642.78 (2020-03-30) MuZero (Res2 Adam) — 557200.75 (2021-04-13) MuZero (Res2 Adam) — 557200.75 (2021-04-13) GDI-I3 — 893110.0 (2021-06-11) GDI-I3 — 893110.0 (2021-06-11) GDI-H3 — 970540.0 (2022-06-07) GDI-I3 — 893110.0 (2022-06-07) GDI-H3 — 970540.0 (2022-06-07) GDI-I3 — 893110.0 (2022-06-07) DNA — 152768.0 (2022-06-20) DNA — 152768.0 (2022-06-20) ASL DDQN — 37026.5 (2023-05-07) ASL DDQN — 37026.5 (2023-05-07) Duel noop — 42214.0 (2015-11-20) Reactor 500M — 223025.0 (2017-04-15) Ape-X — 411943.5 (2018-03-02) CGP — 993010.0 (2018-06-14)
RankModel Score PaperCodeYear
1 CGP 993010 Evolving simple programs for playing Atari games ShuhuaGao/gpFlappyBird · JacobLaney/cgp-tetris 2018
2 GDI-H3 970540 Generalized Data Distribution Iteration 2022
3 GDI-I3 893110 GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 2021
3 GDI-I3 893110 Generalized Data Distribution Iteration 2022
5 MuZero 839642.95 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
6 Agent57 677642.78 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
7 R2D2 665792.0 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
8 MuZero (Res2 Adam) 557200.75 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
9 Ape-X 411943.5 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
10 Reactor 500M 223025.0 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
1–10 / 42 다음 → 페이지당 10 20 50 100