paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Demon Attack

92개 결과 · ⬇ CSV · JSON

Score

325 1.972e+05 3.942e+05 5.911e+05 7.88e+05 2012-07 2026-11 UCT — 28158.8 (2012-07-19) Best Learner — 520.5 (2012-07-19) UCT — 28158.8 (2012-07-19) Best Learner — 520.5 (2012-07-19) Nature DQN — 9711.0 (2015-02-25) Nature DQN — 9711.0 (2015-02-25) Gorila — 14880.1 (2015-07-15) Gorila — 14880.1 (2015-07-15) Prior+Duel hs — 73371.3 (2015-09-22) DDQN (tuned) hs — 69803.4 (2015-09-22) DQN hs — 12550.7 (2015-09-22) DQN noop — 12149.4 (2015-09-22) Prior+Duel hs — 73371.3 (2015-09-22) DDQN (tuned) hs — 69803.4 (2015-09-22) DQN hs — 12550.7 (2015-09-22) DQN noop — 12149.4 (2015-09-22) Prior noop — 71846.4 (2015-11-18) Prior hs — 61277.5 (2015-11-18) Prior noop — 71846.4 (2015-11-18) Prior hs — 61277.5 (2015-11-18) Prior+Duel noop — 72878.6 (2015-11-20) Duel noop — 60813.3 (2015-11-20) DDQN (tuned) noop — 58044.2 (2015-11-20) Duel hs — 56322.8 (2015-11-20) Prior+Duel noop — 72878.6 (2015-11-20) Duel noop — 60813.3 (2015-11-20) DDQN (tuned) noop — 58044.2 (2015-11-20) Duel hs — 56322.8 (2015-11-20) Persistent AL — 70908.17 (2015-12-15) Advantage Learning — 27153.48 (2015-12-15) Persistent AL — 70908.17 (2015-12-15) Advantage Learning — 27153.48 (2015-12-15) A3C LSTM hs — 115201.9 (2016-02-04) A3C FF hs — 113308.4 (2016-02-04) A3C FF (1 day) hs — 84997.5 (2016-02-04) A3C LSTM hs — 115201.9 (2016-02-04) A3C FF hs — 113308.4 (2016-02-04) A3C FF (1 day) hs — 84997.5 (2016-02-04) Bootstrapped DQN — 82610.0 (2016-02-15) Bootstrapped DQN — 82610.0 (2016-02-15) DDQN+Pop-Art noop — 63644.9 (2016-02-24) DDQN+Pop-Art noop — 63644.9 (2016-02-24) ES FF (1 hour) noop — 1166.5 (2017-03-10) ES FF (1 hour) noop — 1166.5 (2017-03-10) Reactor 500M — 115154.0 (2017-04-15) Reactor 500M — 115154.0 (2017-04-15) NoisyNet-Dueling — 69311.0 (2017-06-30) NoisyNet-Dueling — 69311.0 (2017-06-30) C51 noop — 130955.0 (2017-07-21) C51 noop — 130955.0 (2017-07-21) QR-DQN-1 — 121551.0 (2017-10-27) QR-DQN-1 — 121551.0 (2017-10-27) IMPALA (deep) — 132826.98 (2018-02-05) IMPALA (deep) — 132826.98 (2018-02-05) Ape-X — 133086.4 (2018-03-02) Ape-X — 133086.4 (2018-03-02) IDVQ + DRSC + XNES — 325.0 (2018-06-04) IDVQ + DRSC + XNES — 325.0 (2018-06-04) IQN — 128580.0 (2018-06-14) A2C + SIL — 10140.5 (2018-06-14) CGP — 2387.0 (2018-06-14) IQN — 128580.0 (2018-06-14) A2C + SIL — 10140.5 (2018-06-14) CGP — 2387.0 (2018-06-14) POP3D — 61147.33 (2018-07-02) POP3D — 61147.33 (2018-07-02) R2D2 — 140002.3 (2019-05-01) R2D2 — 140002.3 (2019-05-01) MuZero — 143964.26 (2019-11-19) MuZero — 143964.26 (2019-11-19) Agent57 — 143161.44 (2020-03-30) Agent57 — 143161.44 (2020-03-30) CURL — 834.0 (2020-04-08) CURL — 834.0 (2020-04-08) DreamerV2 — 82263.0 (2020-10-05) DreamerV2 — 82263.0 (2020-10-05) MuZero (Res2 Adam) — 143838.04 (2021-04-13) MuZero (Res2 Adam) — 143838.04 (2021-04-13) GDI-I3 — 675530.0 (2021-06-11) GDI-I3 — 675530.0 (2021-06-11) GDI-H3 — 787985.0 (2022-06-07) GDI-I3 — 675530.0 (2022-06-07) GDI-H3 — 787985.0 (2022-06-07) GDI-I3 — 675530.0 (2022-06-07) DNA — 97909.0 (2022-06-20) DNA — 97909.0 (2022-06-20) ASL DDQN — 119773.9 (2023-05-07) ASL DDQN — 119773.9 (2023-05-07) UCT — 28158.8 (2012-07-19) Prior+Duel hs — 73371.3 (2015-09-22) A3C LSTM hs — 115201.9 (2016-02-04) C51 noop — 130955.0 (2017-07-21) IMPALA (deep) — 132826.98 (2018-02-05) Ape-X — 133086.4 (2018-03-02) R2D2 — 140002.3 (2019-05-01) MuZero — 143964.26 (2019-11-19) GDI-I3 — 675530.0 (2021-06-11) GDI-H3 — 787985.0 (2022-06-07)
RankModel Score PaperCodeYear
1 GDI-H3 787985 Generalized Data Distribution Iteration 2022
2 GDI-I3 675530 GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 2021
2 GDI-I3 675530 Generalized Data Distribution Iteration 2022
4 RIMs-PPO 230324
5 MuZero 143964.26 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
6 MuZero (Res2 Adam) 143838.04 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
7 Agent57 143161.44 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
8 R2D2 140002.3 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
9 Ape-X 133086.4 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
10 IMPALA (deep) 132826.98 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
11 C51 noop 130955.0 A Distributional Perspective on Reinforcement Learning facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19 2017
12 IQN 128580 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
13 QR-DQN-1 121551 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
14 ASL DDQN 119773.9 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
15 A3C LSTM hs 115201.9 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
16 Reactor 500M 115154.0 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
17 A3C FF hs 113308.4 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
18 DNA 97909 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
19 A3C FF (1 day) hs 84997.5 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
20 Bootstrapped DQN 82610 Deep Exploration via Bootstrapped DQN tensorflow/models · tensorflow/models · NervanaSystems/coach · +3 2016
1–20 / 92 다음 → 페이지당 10 20 50 100