paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Breakout

116개 결과 · ⬇ CSV · JSON

Score

0.7 216.5 432.3 648.2 864 2012-07 2026-11 UCT — 364.4 (2012-07-19) Best Learner — 5.2 (2012-07-19) UCT — 364.4 (2012-07-19) Best Learner — 5.2 (2012-07-19) DQN Best — 225.0 (2013-12-19) DQN Best — 225.0 (2013-12-19) Nature DQN — 401.2 (2015-02-25) Nature DQN — 401.2 (2015-02-25) Gorila — 313.0 (2015-07-15) Gorila — 313.0 (2015-07-15) DQN noop — 385.5 (2015-09-22) DDQN (tuned) hs — 368.9 (2015-09-22) Prior+Duel hs — 354.6 (2015-09-22) DQN hs — 354.5 (2015-09-22) DQN noop — 385.5 (2015-09-22) DDQN (tuned) hs — 368.9 (2015-09-22) Prior+Duel hs — 354.6 (2015-09-22) DQN hs — 354.5 (2015-09-22) Prior noop — 373.9 (2015-11-18) Prior hs — 343.0 (2015-11-18) Prior noop — 373.9 (2015-11-18) Prior hs — 343.0 (2015-11-18) DDQN (tuned) noop — 418.5 (2015-11-20) Duel hs — 411.6 (2015-11-20) Prior+Duel noop — 366.0 (2015-11-20) Duel noop — 345.3 (2015-11-20) DDQN (tuned) noop — 418.5 (2015-11-20) Duel hs — 411.6 (2015-11-20) Prior+Duel noop — 366.0 (2015-11-20) Duel noop — 345.3 (2015-11-20) DARQN hard — 20.0 (2015-12-05) DARQN hard — 20.0 (2015-12-05) Persistent AL — 431.89 (2015-12-15) Advantage Learning — 425.32 (2015-12-15) Persistent AL — 431.89 (2015-12-15) Advantage Learning — 425.32 (2015-12-15) A3C LSTM hs — 766.8 (2016-02-04) A3C FF hs — 681.9 (2016-02-04) A3C FF (1 day) hs — 551.6 (2016-02-04) A3C LSTM hs — 766.8 (2016-02-04) A3C FF hs — 681.9 (2016-02-04) A3C FF (1 day) hs — 551.6 (2016-02-04) Bootstrapped DQN — 855.0 (2016-02-15) Bootstrapped DQN — 855.0 (2016-02-15) DDQN+Pop-Art noop — 344.1 (2016-02-24) DDQN+Pop-Art noop — 344.1 (2016-02-24) ES FF (1 hour) noop — 9.5 (2017-03-10) ES FF (1 hour) noop — 9.5 (2017-03-10) Reactor 500M — 514.8 (2017-04-15) Reactor 500M — 514.8 (2017-04-15) NoisyNet-Dueling — 263.0 (2017-06-30) NoisyNet-Dueling — 263.0 (2017-06-30) C51 noop — 748.0 (2017-07-21) C51 noop — 748.0 (2017-07-21) MAC — 372.7 (2017-09-01) MAC — 372.7 (2017-09-01) QR-DQN-1 — 742.0 (2017-10-27) QR-DQN-1 — 742.0 (2017-10-27) DDRL A3C — 350.0 (2018-01-09) DDRL A3C — 350.0 (2018-01-09) IMPALA (deep) — 787.34 (2018-02-05) IMPALA (deep) — 787.34 (2018-02-05) Ape-X — 800.9 (2018-03-02) Ape-X — 800.9 (2018-03-02) IQN — 734.0 (2018-06-14) A2C + SIL — 452.0 (2018-06-14) CGP — 13.2 (2018-06-14) IQN — 734.0 (2018-06-14) A2C + SIL — 452.0 (2018-06-14) CGP — 13.2 (2018-06-14) POP3D — 458.41 (2018-07-02) POP3D — 458.41 (2018-07-02) R2D2 — 837.7 (2019-05-01) R2D2 — 837.7 (2019-05-01) SAC — 0.7 (2019-10-16) SAC — 0.7 (2019-10-16) FQF — 854.2 (2019-11-05) FQF — 854.2 (2019-11-05) Agent57 — 790.4 (2020-03-30) Agent57 — 790.4 (2020-03-30) CURL — 18.2 (2020-04-08) CURL — 18.2 (2020-04-08) DreamerV2 — 312.0 (2020-10-05) DreamerV2 — 312.0 (2020-10-05) Discrete Latent Space World Model (VQ-VAE) — 11.6 (2020-10-12) Discrete Latent Space World Model (VQ-VAE) — 11.6 (2020-10-12) SPOS — 180.6 (2020-11-30) ENAS Search space 1 — 161.1 (2020-11-30) SPOS Search space 1 — 144.4 (2020-11-30) ENAS — 91.4 (2020-11-30) SPOS — 180.6 (2020-11-30) ENAS Search space 1 — 161.1 (2020-11-30) SPOS Search space 1 — 144.4 (2020-11-30) ENAS — 91.4 (2020-11-30) Recurrent Rational DQN Average — 336.0 (2021-02-18) Rational DQN Average — 316.0 (2021-02-18) Recurrent Rational DQN Average — 336.0 (2021-02-18) Rational DQN Average — 316.0 (2021-02-18) MuZero (Res2 Adam) — 758.04 (2021-04-13) MuZero (Res2 Adam) — 758.04 (2021-04-13) DT — 267.5 (2021-06-02) DT — 267.5 (2021-06-02) GDI-H3(200M frames) — 864.0 (2022-06-07) GDI-I3(200M frames) — 864.0 (2022-06-07) GDI-I3 — 864.0 (2022-06-07) GDI-H3 — 864.0 (2022-06-07) GDI-H3(200M frames) — 864.0 (2022-06-07) GDI-I3(200M frames) — 864.0 (2022-06-07) GDI-I3 — 864.0 (2022-06-07) GDI-H3 — 864.0 (2022-06-07) DNA — 626.0 (2022-06-20) DNA — 626.0 (2022-06-20) ASL DDQN — 621.7 (2023-05-07) ASL DDQN — 621.7 (2023-05-07) UCT — 364.4 (2012-07-19) Nature DQN — 401.2 (2015-02-25) DDQN (tuned) noop — 418.5 (2015-11-20) Persistent AL — 431.89 (2015-12-15) A3C LSTM hs — 766.8 (2016-02-04) Bootstrapped DQN — 855.0 (2016-02-15) GDI-H3(200M frames) — 864.0 (2022-06-07)
RankModel Score PaperCodeYear
1 GDI-H3(200M frames) 864.00 Generalized Data Distribution Iteration 2022
1 GDI-I3(200M frames) 864.00 Generalized Data Distribution Iteration 2022
1 GDI-I3 864.00 Generalized Data Distribution Iteration 2022
1 GDI-H3 864 Generalized Data Distribution Iteration 2022
5 Bootstrapped DQN 855 Deep Exploration via Bootstrapped DQN tensorflow/models · tensorflow/models · NervanaSystems/coach · +3 2016
6 FQF 854.2 Fully Parameterized Quantile Function for Distributional Reinforcement Learning opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3 2019
7 R2D2 837.7 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
8 Ape-X 800.9 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
9 Agent57 790.4 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
10 IMPALA (deep) 787.34 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
11 A3C LSTM hs 766.8 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
12 MuZero (Res2 Adam) 758.04 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
13 C51 noop 748.0 A Distributional Perspective on Reinforcement Learning facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19 2017
14 QR-DQN-1 742 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
15 IQN 734 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
16 A3C FF hs 681.9 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
17 DNA 626 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
18 ASL DDQN 621.7 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
19 A3C FF (1 day) hs 551.6 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
20 Reactor 500M 514.8 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
1–20 / 116 다음 → 페이지당 10 20 50 100