paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Enduro

96개 결과 · ⬇ CSV · JSON

Score

-82.5 3521 7124 1.073e+04 1.433e+04 2012-07 2026-11 UCT — 286.3 (2012-07-19) Best Learner — 129.1 (2012-07-19) UCT — 286.3 (2012-07-19) Best Learner — 129.1 (2012-07-19) DQN Best — 661.0 (2013-12-19) DQN Best — 661.0 (2013-12-19) Nature DQN — 301.8 (2015-02-25) Nature DQN — 301.8 (2015-02-25) Gorila — 71.0 (2015-07-15) Gorila — 71.0 (2015-07-15) Prior+Duel hs — 2223.9 (2015-09-22) DDQN (tuned) hs — 1216.6 (2015-09-22) DQN noop — 729.0 (2015-09-22) DQN hs — 626.7 (2015-09-22) Prior+Duel hs — 2223.9 (2015-09-22) DDQN (tuned) hs — 1216.6 (2015-09-22) DQN noop — 729.0 (2015-09-22) DQN hs — 626.7 (2015-09-22) Prior noop — 2093.0 (2015-11-18) Prior hs — 1831.0 (2015-11-18) Prior noop — 2093.0 (2015-11-18) Prior hs — 1831.0 (2015-11-18) Prior+Duel noop — 2306.4 (2015-11-20) Duel noop — 2258.2 (2015-11-20) Duel hs — 2077.4 (2015-11-20) DDQN (tuned) noop — 1211.8 (2015-11-20) Prior+Duel noop — 2306.4 (2015-11-20) Duel noop — 2258.2 (2015-11-20) Duel hs — 2077.4 (2015-11-20) DDQN (tuned) noop — 1211.8 (2015-11-20) Persistent AL — 1343.1 (2015-12-15) Advantage Learning — 1252.7 (2015-12-15) Persistent AL — 1343.1 (2015-12-15) Advantage Learning — 1252.7 (2015-12-15) A3C FF (1 day) hs — -82.2 (2016-02-04) A3C FF hs — -82.5 (2016-02-04) A3C LSTM hs — -82.5 (2016-02-04) A3C FF (1 day) hs — -82.2 (2016-02-04) A3C FF hs — -82.5 (2016-02-04) A3C LSTM hs — -82.5 (2016-02-04) Bootstrapped DQN — 1591.0 (2016-02-15) Bootstrapped DQN — 1591.0 (2016-02-15) DDQN+Pop-Art noop — 2002.1 (2016-02-24) DDQN+Pop-Art noop — 2002.1 (2016-02-24) ES FF (1 hour) noop — 95.0 (2017-03-10) ES FF (1 hour) noop — 95.0 (2017-03-10) Reactor 500M — 2224.2 (2017-04-15) Reactor 500M — 2224.2 (2017-04-15) NoisyNet-Dueling — 2013.0 (2017-06-30) NoisyNet-Dueling — 2013.0 (2017-06-30) VPN — 382.0 (2017-07-11) VPN — 382.0 (2017-07-11) C51 noop — 3454.0 (2017-07-21) C51 noop — 3454.0 (2017-07-21) QR-DQN-1 — 2355.0 (2017-10-27) QR-DQN-1 — 2355.0 (2017-10-27) IMPALA (deep) — 0.0 (2018-02-05) IMPALA (deep) — 0.0 (2018-02-05) Ape-X — 2177.4 (2018-03-02) Ape-X — 2177.4 (2018-03-02) IQN — 2359.0 (2018-06-14) A2C + SIL — 1205.1 (2018-06-14) CGP — 56.8 (2018-06-14) IQN — 2359.0 (2018-06-14) A2C + SIL — 1205.1 (2018-06-14) CGP — 56.8 (2018-06-14) POP3D — 459.85 (2018-07-02) POP3D — 459.85 (2018-07-02) R2D2 — 2372.7 (2019-05-01) R2D2 — 2372.7 (2019-05-01) SAC — 0.8 (2019-10-16) SAC — 0.8 (2019-10-16) MuZero — 2382.44 (2019-11-19) MuZero — 2382.44 (2019-11-19) Agent57 — 2367.71 (2020-03-30) Agent57 — 2367.71 (2020-03-30) DreamerV2 — 1656.0 (2020-10-05) DreamerV2 — 1656.0 (2020-10-05) Rational DQN Average — 1043.0 (2021-02-18) Recurrent Rational DQN Average — 957.0 (2021-02-18) Rational DQN Average — 1043.0 (2021-02-18) Recurrent Rational DQN Average — 957.0 (2021-02-18) MuZero (Res2 Adam) — 2365.81 (2021-04-13) MuZero (Res2 Adam) — 2365.81 (2021-04-13) GDI-I3 — 14330.0 (2021-06-11) GDI-I3 — 14330.0 (2021-06-11) GDI-I3 — 14330.0 (2022-06-07) GDI-H3 — 14300.0 (2022-06-07) GDI-I3 — 14330.0 (2022-06-07) GDI-H3 — 14300.0 (2022-06-07) DNA — 2059.0 (2022-06-20) DNA — 2059.0 (2022-06-20) ASL DDQN — 2103.1 (2023-05-07) ASL DDQN — 2103.1 (2023-05-07) UCT — 286.3 (2012-07-19) DQN Best — 661.0 (2013-12-19) Prior+Duel hs — 2223.9 (2015-09-22) Prior+Duel noop — 2306.4 (2015-11-20) C51 noop — 3454.0 (2017-07-21) GDI-I3 — 14330.0 (2021-06-11)
RankModel Score PaperCodeYear
1 GDI-I3 14330 GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 2021
1 GDI-I3 14330 Generalized Data Distribution Iteration 2022
3 GDI-H3 14300 Generalized Data Distribution Iteration 2022
4 C51 noop 3454.0 A Distributional Perspective on Reinforcement Learning facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19 2017
5 MuZero 2382.44 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
6 R2D2 2372.7 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
7 Agent57 2367.71 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
8 MuZero (Res2 Adam) 2365.81 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
9 IQN 2359 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
10 QR-DQN-1 2355 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
11 Prior+Duel noop 2306.4 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
12 Duel noop 2258.2 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
13 Reactor 500M 2224.2 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
14 Prior+Duel hs 2223.9 Deep Reinforcement Learning with Double Q-learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94 2015
15 Ape-X 2177.4 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
16 ASL DDQN 2103.1 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
17 Prior noop 2093.0 Prioritized Experience Replay labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74 2015
18 Duel hs 2077.4 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
19 DNA 2059 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
20 NoisyNet-Dueling 2013 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
1–20 / 96 다음 → 페이지당 10 20 50 100