paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Alien

98개 결과 · ⬇ CSV · JSON

Score

182.1 1.856e+05 3.71e+05 5.564e+05 7.418e+05 2012-07 2026-11 UCT — 7785.0 (2012-07-19) Best Learner — 939.2 (2012-07-19) UCT — 7785.0 (2012-07-19) Best Learner — 939.2 (2012-07-19) Nature DQN — 3069.0 (2015-02-25) Nature DQN — 3069.0 (2015-02-25) Gorila — 813.5 (2015-07-15) Gorila — 813.5 (2015-07-15) DQN noop — 1620.0 (2015-09-22) DDQN (tuned) hs — 1033.4 (2015-09-22) Prior+Duel hs — 823.7 (2015-09-22) DQN hs — 634.0 (2015-09-22) DQN noop — 1620.0 (2015-09-22) DDQN (tuned) hs — 1033.4 (2015-09-22) Prior+Duel hs — 823.7 (2015-09-22) DQN hs — 634.0 (2015-09-22) Prior noop — 4203.8 (2015-11-18) Prior hs — 1334.7 (2015-11-18) Prior noop — 4203.8 (2015-11-18) Prior hs — 1334.7 (2015-11-18) Duel noop — 4461.4 (2015-11-20) Prior+Duel noop — 3941.0 (2015-11-20) DDQN (tuned) noop — 3747.7 (2015-11-20) Duel hs — 1486.5 (2015-11-20) Prior+Duel hs — 823.7 (2015-11-20) Duel noop — 4461.4 (2015-11-20) Prior+Duel noop — 3941.0 (2015-11-20) DDQN (tuned) noop — 3747.7 (2015-11-20) Duel hs — 1486.5 (2015-11-20) Prior+Duel hs — 823.7 (2015-11-20) Persistent AL — 5699.81 (2015-12-15) Advantage Learning — 4990.91 (2015-12-15) Persistent AL — 5699.81 (2015-12-15) Advantage Learning — 4990.91 (2015-12-15) A3C LSTM hs — 945.3 (2016-02-04) A3C FF hs — 518.4 (2016-02-04) A3C FF (1 day) hs — 182.1 (2016-02-04) A3C LSTM hs — 945.3 (2016-02-04) A3C FF hs — 518.4 (2016-02-04) A3C FF (1 day) hs — 182.1 (2016-02-04) Bootstrapped DQN — 2436.6 (2016-02-15) Bootstrapped DQN — 2436.6 (2016-02-15) DDQN+Pop-Art noop — 3213.5 (2016-02-24) DDQN+Pop-Art noop — 3213.5 (2016-02-24) ES FF (1 hour) noop — 994.0 (2017-03-10) ES FF (1 hour) noop — 994.0 (2017-03-10) Reactor 500M — 12689.1 (2017-04-15) Reactor 500M — 12689.1 (2017-04-15) NoisyNet-Dueling — 5778.0 (2017-06-30) NoisyNet-Dueling — 5778.0 (2017-06-30) VPN — 1429.0 (2017-07-11) VPN — 1429.0 (2017-07-11) C51 noop — 3166.0 (2017-07-21) C51 noop — 3166.0 (2017-07-21) QR-DQN-1 — 4871.0 (2017-10-27) QR-DQN-1 — 4871.0 (2017-10-27) IMPALA (deep) — 15962.1 (2018-02-05) IMPALA (deep) — 15962.1 (2018-02-05) Ape-X — 40804.9 (2018-03-02) Ape-X — 40804.9 (2018-03-02) IQN — 7022.0 (2018-06-14) A2C + SIL — 2242.2 (2018-06-14) CGP — 1978.0 (2018-06-14) IQN — 7022.0 (2018-06-14) A2C + SIL — 2242.2 (2018-06-14) CGP — 1978.0 (2018-06-14) POP3D — 1510.8 (2018-07-02) POP3D — 1510.8 (2018-07-02) R2D2 — 229496.9 (2019-05-01) R2D2 — 229496.9 (2019-05-01) SAC — 216.9 (2019-10-16) SAC — 216.9 (2019-10-16) FQF — 16754.6 (2019-11-05) FQF — 16754.6 (2019-11-05) MuZero — 741812.63 (2019-11-19) MuZero — 741812.63 (2019-11-19) Agent57 — 297638.17 (2020-03-30) Agent57 — 297638.17 (2020-03-30) CURL — 1148.2 (2020-04-08) CURL — 1148.2 (2020-04-08) DreamerV2 — 3967.0 (2020-10-05) DreamerV2 — 3967.0 (2020-10-05) Rainbow+SEER — 1172.6 (2021-03-04) Rainbow+SEER — 1172.6 (2021-03-04) MuZero (Res2 Adam) — 70192.35 (2021-04-13) MuZero (Res2 Adam) — 70192.35 (2021-04-13) GDI-H3(1B frames) — 279700.0 (2021-11-24) GDI-H3(1B frames) — 279700.0 (2021-11-24) GDI-H3 — 48735.0 (2022-06-07) GDI-I3 — 43384.0 (2022-06-07) GDI-H3 — 48735.0 (2022-06-07) GDI-I3 — 43384.0 (2022-06-07) DNA — 5021.0 (2022-06-20) DNA — 5021.0 (2022-06-20) ASL DDQN — 6955.2 (2023-05-07) ASL DDQN — 6955.2 (2023-05-07) UCT — 7785.0 (2012-07-19) Reactor 500M — 12689.1 (2017-04-15) IMPALA (deep) — 15962.1 (2018-02-05) Ape-X — 40804.9 (2018-03-02) R2D2 — 229496.9 (2019-05-01) MuZero — 741812.63 (2019-11-19)
RankModel Score PaperCodeYear
1 MuZero 741812.63 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
2 Agent57 297638.17 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
3 GDI-H3(1B frames) 279700 GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning 2021
4 R2D2 229496.9 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
5 MuZero (Res2 Adam) 70192.35 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
6 GDI-H3 48735 Generalized Data Distribution Iteration 2022
7 GDI-I3 43384 Generalized Data Distribution Iteration 2022
8 Ape-X 40804.9 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
9 FQF 16754.6 Fully Parameterized Quantile Function for Distributional Reinforcement Learning opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3 2019
10 IMPALA (deep) 15962.10 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
11 Reactor 500M 12689.1 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
12 UCT 7785 The Arcade Learning Environment: An Evaluation Platform for General Agents mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory 2012
13 IQN 7022 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
14 ASL DDQN 6955.2 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
15 NoisyNet-Dueling 5778 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
16 Persistent AL 5699.81 Increasing the Action Gap: New Operators for Reinforcement Learning janhuenermann/neurojs · chainer/chainerrl 2015
17 DNA 5021 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
18 Advantage Learning 4990.91 Increasing the Action Gap: New Operators for Reinforcement Learning janhuenermann/neurojs · chainer/chainerrl 2015
19 QR-DQN-1 4871 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
20 Duel noop 4461.4 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
1–20 / 98 다음 → 페이지당 10 20 50 100