paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Road Runner

88개 결과 · ⬇ CSV · JSON

Score

67.7 2.501e+05 5e+05 7.5e+05 1e+06 2012-07 2026-11 UCT — 38725.0 (2012-07-19) Best Learner — 67.7 (2012-07-19) UCT — 38725.0 (2012-07-19) Best Learner — 67.7 (2012-07-19) Nature DQN — 18257.0 (2015-02-25) Nature DQN — 18257.0 (2015-02-25) Gorila — 43079.8 (2015-07-15) Gorila — 43079.8 (2015-07-15) Prior+Duel hs — 54630.0 (2015-09-22) DDQN (tuned) hs — 43156.0 (2015-09-22) DQN noop — 39544.0 (2015-09-22) DQN hs — 35215.0 (2015-09-22) Prior+Duel hs — 54630.0 (2015-09-22) DDQN (tuned) hs — 43156.0 (2015-09-22) DQN noop — 39544.0 (2015-09-22) DQN hs — 35215.0 (2015-09-22) Prior noop — 57608.0 (2015-11-18) Prior hs — 52264.0 (2015-11-18) Prior noop — 57608.0 (2015-11-18) Prior hs — 52264.0 (2015-11-18) Duel noop — 69524.0 (2015-11-20) Prior+Duel noop — 62151.0 (2015-11-20) Duel hs — 58549.0 (2015-11-20) DDQN (tuned) noop — 44127.0 (2015-11-20) Duel noop — 69524.0 (2015-11-20) Prior+Duel noop — 62151.0 (2015-11-20) Duel hs — 58549.0 (2015-11-20) DDQN (tuned) noop — 44127.0 (2015-11-20) Advantage Learning — 52351.23 (2015-12-15) Advantage Learning — 52351.23 (2015-12-15) A3C LSTM hs — 73949.0 (2016-02-04) A3C FF hs — 34216.0 (2016-02-04) A3C FF (1 day) hs — 31769.0 (2016-02-04) A3C LSTM hs — 73949.0 (2016-02-04) A3C FF hs — 34216.0 (2016-02-04) A3C FF (1 day) hs — 31769.0 (2016-02-04) Bootstrapped DQN — 51500.0 (2016-02-15) Bootstrapped DQN — 51500.0 (2016-02-15) DDQN+Pop-Art noop — 47770.0 (2016-02-24) DDQN+Pop-Art noop — 47770.0 (2016-02-24) ES FF (1 hour) noop — 16590.0 (2017-03-10) ES FF (1 hour) noop — 16590.0 (2017-03-10) NoisyNet-Dueling — 234352.0 (2017-06-30) NoisyNet-Dueling — 234352.0 (2017-06-30) C51 noop — 55839.0 (2017-07-21) C51 noop — 55839.0 (2017-07-21) QR-DQN-1 — 64262.0 (2017-10-27) QR-DQN-1 — 64262.0 (2017-10-27) IMPALA (deep) — 57121.0 (2018-02-05) IMPALA (deep) — 57121.0 (2018-02-05) Ape-X — 222234.5 (2018-03-02) Ape-X — 222234.5 (2018-03-02) IQN — 57900.0 (2018-06-14) A2C + SIL — 57071.7 (2018-06-14) CGP — 8960.0 (2018-06-14) IQN — 57900.0 (2018-06-14) A2C + SIL — 57071.7 (2018-06-14) CGP — 8960.0 (2018-06-14) POP3D — 44679.67 (2018-07-02) POP3D — 44679.67 (2018-07-02) R2D2 — 599246.7 (2019-05-01) R2D2 — 599246.7 (2019-05-01) SAC — 305.3 (2019-10-16) SAC — 305.3 (2019-10-16) MuZero — 613411.8 (2019-11-19) MuZero — 613411.8 (2019-11-19) Agent57 — 243025.8 (2020-03-30) Agent57 — 243025.8 (2020-03-30) CURL — 6786.7 (2020-04-08) CURL — 6786.7 (2020-04-08) DreamerV2 — 203576.0 (2020-10-05) DreamerV2 — 203576.0 (2020-10-05) Rainbow+SEER — 11794.0 (2021-03-04) Rainbow+SEER — 11794.0 (2021-03-04) MuZero (Res2 Adam) — 531097.0 (2021-04-13) MuZero (Res2 Adam) — 531097.0 (2021-04-13) GDI-I3 — 878600.0 (2021-06-11) GDI-I3 — 878600.0 (2021-06-11) GDI-H3 — 999999.0 (2022-06-07) GDI-I3 — 878600.0 (2022-06-07) GDI-H3 — 999999.0 (2022-06-07) GDI-I3 — 878600.0 (2022-06-07) DNA — 61713.0 (2022-06-20) DNA — 61713.0 (2022-06-20) ASL DDQN — 56520.0 (2023-05-07) ASL DDQN — 56520.0 (2023-05-07) UCT — 38725.0 (2012-07-19) Gorila — 43079.8 (2015-07-15) Prior+Duel hs — 54630.0 (2015-09-22) Prior noop — 57608.0 (2015-11-18) Duel noop — 69524.0 (2015-11-20) A3C LSTM hs — 73949.0 (2016-02-04) NoisyNet-Dueling — 234352.0 (2017-06-30) R2D2 — 599246.7 (2019-05-01) MuZero — 613411.8 (2019-11-19) GDI-I3 — 878600.0 (2021-06-11) GDI-H3 — 999999.0 (2022-06-07)
RankModel Score PaperCodeYear
1 GDI-H3 999999 Generalized Data Distribution Iteration 2022
2 GDI-I3 878600 GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 2021
2 GDI-I3 878600 Generalized Data Distribution Iteration 2022
4 MuZero 613411.80 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
5 R2D2 599246.7 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
6 MuZero (Res2 Adam) 531097 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
7 Agent57 243025.8 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
8 NoisyNet-Dueling 234352 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
9 Ape-X 222234.5 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
10 DreamerV2 203576 Mastering Atari with Discrete World Models opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6 2020
11 A3C LSTM hs 73949.0 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
12 Duel noop 69524.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
13 QR-DQN-1 64262 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
14 Prior+Duel noop 62151.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
15 DNA 61713 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
16 Duel hs 58549.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
17 IQN 57900 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
18 Prior noop 57608.0 Prioritized Experience Replay labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74 2015
19 IMPALA (deep) 57121.00 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
20 A2C + SIL 57071.7 Self-Imitation Learning junhyukoh/self-imitation-learning · rwightman/pytorch-opensim-rl · SeungeonBaek/continuous-agents-test · +1 2018
1–20 / 88 다음 → 페이지당 10 20 50 100