paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Asteroids

86개 결과 · ⬇ CSV · JSON

Score

734.7 1.906e+05 3.804e+05 5.702e+05 7.6e+05 2012-07 2026-11 UCT — 4660.6 (2012-07-19) Best Learner — 907.3 (2012-07-19) UCT — 4660.6 (2012-07-19) Best Learner — 907.3 (2012-07-19) Nature DQN — 1629.0 (2015-02-25) Nature DQN — 1629.0 (2015-02-25) Gorila — 933.6 (2015-07-15) Gorila — 933.6 (2015-07-15) DQN hs — 1458.7 (2015-09-22) DQN noop — 1364.5 (2015-09-22) DDQN (tuned) hs — 1193.2 (2015-09-22) Prior+Duel hs — 1021.9 (2015-09-22) DQN hs — 1458.7 (2015-09-22) DQN noop — 1364.5 (2015-09-22) DDQN (tuned) hs — 1193.2 (2015-09-22) Prior+Duel hs — 1021.9 (2015-09-22) Prior noop — 2654.3 (2015-11-18) Prior hs — 1745.1 (2015-11-18) Prior noop — 2654.3 (2015-11-18) Prior hs — 1745.1 (2015-11-18) Duel noop — 2837.7 (2015-11-20) Duel hs — 2035.4 (2015-11-20) Prior+Duel noop — 1192.7 (2015-11-20) DDQN (tuned) noop — 734.7 (2015-11-20) Duel noop — 2837.7 (2015-11-20) Duel hs — 2035.4 (2015-11-20) Prior+Duel noop — 1192.7 (2015-11-20) DDQN (tuned) noop — 734.7 (2015-11-20) Advantage Learning — 1924.42 (2015-12-15) Persistent AL — 1673.52 (2015-12-15) Advantage Learning — 1924.42 (2015-12-15) Persistent AL — 1673.52 (2015-12-15) A3C LSTM hs — 5093.1 (2016-02-04) A3C FF hs — 4474.5 (2016-02-04) A3C FF (1 day) hs — 3009.4 (2016-02-04) A3C LSTM hs — 5093.1 (2016-02-04) A3C FF hs — 4474.5 (2016-02-04) A3C FF (1 day) hs — 3009.4 (2016-02-04) Bootstrapped DQN — 1032.0 (2016-02-15) Bootstrapped DQN — 1032.0 (2016-02-15) DDQN+Pop-Art noop — 2869.3 (2016-02-24) DDQN+Pop-Art noop — 2869.3 (2016-02-24) ES FF (1 hour) noop — 1562.0 (2017-03-10) ES FF (1 hour) noop — 1562.0 (2017-03-10) Reactor 500M — 3726.1 (2017-04-15) Reactor 500M — 3726.1 (2017-04-15) NoisyNet-Dueling — 86700.0 (2017-06-30) NoisyNet-Dueling — 86700.0 (2017-06-30) C51 noop — 1516.0 (2017-07-21) C51 noop — 1516.0 (2017-07-21) QR-DQN-1 — 4226.0 (2017-10-27) QR-DQN-1 — 4226.0 (2017-10-27) IMPALA (deep) — 108590.05 (2018-02-05) IMPALA (deep) — 108590.05 (2018-02-05) Ape-X — 155495.1 (2018-03-02) Ape-X — 155495.1 (2018-03-02) CGP — 9412.0 (2018-06-14) IQN — 2898.0 (2018-06-14) A2C + SIL — 2259.4 (2018-06-14) CGP — 9412.0 (2018-06-14) IQN — 2898.0 (2018-06-14) A2C + SIL — 2259.4 (2018-06-14) POP3D — 2488.1 (2018-07-02) POP3D — 2488.1 (2018-07-02) R2D2 — 357867.7 (2019-05-01) R2D2 — 357867.7 (2019-05-01) FQF — 4553.0 (2019-11-05) FQF — 4553.0 (2019-11-05) MuZero — 678558.64 (2019-11-19) MuZero — 678558.64 (2019-11-19) Agent57 — 150854.61 (2020-03-30) Agent57 — 150854.61 (2020-03-30) DreamerV2 — 41526.0 (2020-10-05) DreamerV2 — 41526.0 (2020-10-05) MuZero (Res2 Adam) — 476412.0 (2021-04-13) MuZero (Res2 Adam) — 476412.0 (2021-04-13) GDI-H3 — 760005.0 (2022-06-07) GDI-I3 — 751970.0 (2022-06-07) GDI-H3 — 760005.0 (2022-06-07) GDI-I3 — 751970.0 (2022-06-07) DNA — 165973.0 (2022-06-20) DNA — 165973.0 (2022-06-20) ASL DDQN — 1984.5 (2023-05-07) ASL DDQN — 1984.5 (2023-05-07) UCT — 4660.6 (2012-07-19) A3C LSTM hs — 5093.1 (2016-02-04) NoisyNet-Dueling — 86700.0 (2017-06-30) IMPALA (deep) — 108590.05 (2018-02-05) Ape-X — 155495.1 (2018-03-02) R2D2 — 357867.7 (2019-05-01) MuZero — 678558.64 (2019-11-19) GDI-H3 — 760005.0 (2022-06-07)
RankModel Score PaperCodeYear
1 GDI-H3 760005 Generalized Data Distribution Iteration 2022
2 GDI-I3 751970 Generalized Data Distribution Iteration 2022
3 MuZero 678558.64 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
4 MuZero (Res2 Adam) 476412 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
5 R2D2 357867.7 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
6 DNA 165973 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
7 Ape-X 155495.1 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
8 Agent57 150854.61 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
9 IMPALA (deep) 108590.05 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
10 NoisyNet-Dueling 86700 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
11 DreamerV2 41526 Mastering Atari with Discrete World Models opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6 2020
12 CGP 9412 Evolving simple programs for playing Atari games ShuhuaGao/gpFlappyBird · JacobLaney/cgp-tetris 2018
13 A3C LSTM hs 5093.1 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
14 UCT 4660.6 The Arcade Learning Environment: An Evaluation Platform for General Agents mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory 2012
15 FQF 4553.0 Fully Parameterized Quantile Function for Distributional Reinforcement Learning opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3 2019
16 A3C FF hs 4474.5 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
17 QR-DQN-1 4226 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
18 Reactor 500M 3726.1 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
19 A3C FF (1 day) hs 3009.4 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
20 IQN 2898 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
1–20 / 86 다음 → 페이지당 10 20 50 100