paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Gopher

86개 결과 · ⬇ CSV · JSON

Score

582 1.226e+05 2.447e+05 3.668e+05 4.888e+05 2012-07 2026-11 UCT — 20560.0 (2012-07-19) Best Learner — 1288.3 (2012-07-19) UCT — 20560.0 (2012-07-19) Best Learner — 1288.3 (2012-07-19) Nature DQN — 8520.0 (2015-02-25) Nature DQN — 8520.0 (2015-02-25) Gorila — 4373.0 (2015-07-15) Gorila — 4373.0 (2015-07-15) Prior+Duel hs — 105148.4 (2015-09-22) DDQN (tuned) hs — 15253.0 (2015-09-22) DQN noop — 8777.4 (2015-09-22) DQN hs — 8190.4 (2015-09-22) Prior+Duel hs — 105148.4 (2015-09-22) DDQN (tuned) hs — 15253.0 (2015-09-22) DQN noop — 8777.4 (2015-09-22) DQN hs — 8190.4 (2015-09-22) Prior hs — 34858.8 (2015-11-18) Prior noop — 32487.2 (2015-11-18) Prior hs — 34858.8 (2015-11-18) Prior noop — 32487.2 (2015-11-18) Prior+Duel noop — 104368.2 (2015-11-20) Duel hs — 20051.4 (2015-11-20) Duel noop — 15718.4 (2015-11-20) DDQN (tuned) noop — 14840.8 (2015-11-20) Prior+Duel noop — 104368.2 (2015-11-20) Duel hs — 20051.4 (2015-11-20) Duel noop — 15718.4 (2015-11-20) DDQN (tuned) noop — 14840.8 (2015-11-20) DARQN soft — 5356.0 (2015-12-05) DARQN soft — 5356.0 (2015-12-05) Advantage Learning — 11912.68 (2015-12-15) Persistent AL — 10611.81 (2015-12-15) Advantage Learning — 11912.68 (2015-12-15) Persistent AL — 10611.81 (2015-12-15) A3C LSTM hs — 17106.8 (2016-02-04) A3C FF hs — 10022.8 (2016-02-04) A3C FF (1 day) hs — 8442.8 (2016-02-04) A3C LSTM hs — 17106.8 (2016-02-04) A3C FF hs — 10022.8 (2016-02-04) A3C FF (1 day) hs — 8442.8 (2016-02-04) Bootstrapped DQN — 17438.4 (2016-02-15) Bootstrapped DQN — 17438.4 (2016-02-15) DDQN+Pop-Art noop — 56218.2 (2016-02-24) DDQN+Pop-Art noop — 56218.2 (2016-02-24) ES FF (1 hour) noop — 582.0 (2017-03-10) ES FF (1 hour) noop — 582.0 (2017-03-10) NoisyNet-Dueling — 38909.0 (2017-06-30) NoisyNet-Dueling — 38909.0 (2017-06-30) C51 noop — 33641.0 (2017-07-21) C51 noop — 33641.0 (2017-07-21) QR-DQN-1 — 113585.0 (2017-10-27) QR-DQN-1 — 113585.0 (2017-10-27) IMPALA (deep) — 66782.3 (2018-02-05) IMPALA (deep) — 66782.3 (2018-02-05) Ape-X — 120500.9 (2018-03-02) Ape-X — 120500.9 (2018-03-02) IQN — 118365.0 (2018-06-14) A2C + SIL — 23304.2 (2018-06-14) CGP — 1696.0 (2018-06-14) IQN — 118365.0 (2018-06-14) A2C + SIL — 23304.2 (2018-06-14) CGP — 1696.0 (2018-06-14) POP3D — 6207.0 (2018-07-02) POP3D — 6207.0 (2018-07-02) R2D2 — 124776.3 (2019-05-01) R2D2 — 124776.3 (2019-05-01) MuZero — 130345.58 (2019-11-19) MuZero — 130345.58 (2019-11-19) Agent57 — 117777.08 (2020-03-30) Agent57 — 117777.08 (2020-03-30) CURL — 801.4 (2020-04-08) CURL — 801.4 (2020-04-08) DreamerV2 — 92282.0 (2020-10-05) DreamerV2 — 92282.0 (2020-10-05) MuZero (Res2 Adam) — 122882.5 (2021-04-13) MuZero (Res2 Adam) — 122882.5 (2021-04-13) GDI-I3 — 488830.0 (2022-06-07) GDI-H3 — 473560.0 (2022-06-07) GDI-I3 — 488830.0 (2022-06-07) GDI-H3 — 473560.0 (2022-06-07) DNA — 80104.0 (2022-06-20) DNA — 80104.0 (2022-06-20) ASL DDQN — 103514.4 (2023-05-07) ASL DDQN — 103514.4 (2023-05-07) UCT — 20560.0 (2012-07-19) Prior+Duel hs — 105148.4 (2015-09-22) QR-DQN-1 — 113585.0 (2017-10-27) Ape-X — 120500.9 (2018-03-02) R2D2 — 124776.3 (2019-05-01) MuZero — 130345.58 (2019-11-19) GDI-I3 — 488830.0 (2022-06-07)
RankModel Score PaperCodeYear
1 GDI-I3 488830 Generalized Data Distribution Iteration 2022
2 GDI-H3 473560 Generalized Data Distribution Iteration 2022
3 MuZero 130345.58 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
4 R2D2 124776.3 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
5 MuZero (Res2 Adam) 122882.5 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
6 Ape-X 120500.9 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
7 IQN 118365 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
8 Agent57 117777.08 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
9 QR-DQN-1 113585 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
10 Prior+Duel hs 105148.4 Deep Reinforcement Learning with Double Q-learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94 2015
11 Prior+Duel noop 104368.2 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
12 ASL DDQN 103514.4 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
13 DreamerV2 92282 Mastering Atari with Discrete World Models opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6 2020
14 DNA 80104 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
15 IMPALA (deep) 66782.30 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
16 DDQN+Pop-Art noop 56218.2 Learning values across many orders of magnitude 2016
17 NoisyNet-Dueling 38909 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
18 Prior hs 34858.8 Prioritized Experience Replay labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74 2015
19 C51 noop 33641.0 A Distributional Perspective on Reinforcement Learning facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19 2017
20 Prior noop 32487.2 Prioritized Experience Replay labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74 2015
1–20 / 86 다음 → 페이지당 10 20 50 100