paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Assault

90개 결과 · ⬇ CSV · JSON

Score

350 3.626e+04 7.216e+04 1.081e+05 1.44e+05 2012-07 2026-11 UCT — 1512.2 (2012-07-19) Best Learner — 628.0 (2012-07-19) UCT — 1512.2 (2012-07-19) Best Learner — 628.0 (2012-07-19) Nature DQN — 3359.0 (2015-02-25) Nature DQN — 3359.0 (2015-02-25) Gorila — 1195.8 (2015-07-15) Gorila — 1195.8 (2015-07-15) Prior+Duel hs — 10950.6 (2015-09-22) DDQN (tuned) hs — 6060.8 (2015-09-22) DQN noop — 4280.4 (2015-09-22) DQN hs — 3489.3 (2015-09-22) Prior+Duel hs — 10950.6 (2015-09-22) DDQN (tuned) hs — 6060.8 (2015-09-22) DQN noop — 4280.4 (2015-09-22) DQN hs — 3489.3 (2015-09-22) Prior noop — 7672.1 (2015-11-18) Prior hs — 6548.9 (2015-11-18) Prior noop — 7672.1 (2015-11-18) Prior hs — 6548.9 (2015-11-18) Prior+Duel noop — 11477.0 (2015-11-20) Prior+Duel hs — 10950.6 (2015-11-20) DDQN (tuned) noop — 5393.2 (2015-11-20) Duel noop — 4621.0 (2015-11-20) Duel hs — 3994.8 (2015-11-20) Prior+Duel noop — 11477.0 (2015-11-20) Prior+Duel hs — 10950.6 (2015-11-20) DDQN (tuned) noop — 5393.2 (2015-11-20) Duel noop — 4621.0 (2015-11-20) Duel hs — 3994.8 (2015-11-20) Advantage Learning — 3661.51 (2015-12-15) Persistent AL — 3304.33 (2015-12-15) Advantage Learning — 3661.51 (2015-12-15) Persistent AL — 3304.33 (2015-12-15) A3C LSTM hs — 14497.9 (2016-02-04) A3C FF hs — 5474.9 (2016-02-04) A3C FF (1 day) hs — 3746.1 (2016-02-04) A3C LSTM hs — 14497.9 (2016-02-04) A3C FF hs — 5474.9 (2016-02-04) A3C FF (1 day) hs — 3746.1 (2016-02-04) Bootstrapped DQN — 8047.1 (2016-02-15) Bootstrapped DQN — 8047.1 (2016-02-15) DDQN+Pop-Art noop — 9011.6 (2016-02-24) DDQN+Pop-Art noop — 9011.6 (2016-02-24) ES FF (1 hour) noop — 1673.9 (2017-03-10) ES FF (1 hour) noop — 1673.9 (2017-03-10) Reactor 500M — 8323.3 (2017-04-15) Reactor 500M — 8323.3 (2017-04-15) NoisyNet-Dueling — 11231.0 (2017-06-30) NoisyNet-Dueling — 11231.0 (2017-06-30) C51 noop — 7203.0 (2017-07-21) C51 noop — 7203.0 (2017-07-21) QR-DQN-1 — 22012.0 (2017-10-27) QR-DQN-1 — 22012.0 (2017-10-27) IMPALA (deep) — 19148.47 (2018-02-05) IMPALA (deep) — 19148.47 (2018-02-05) Ape-X — 24559.4 (2018-03-02) Ape-X — 24559.4 (2018-03-02) IQN — 29091.0 (2018-06-14) A2C + SIL — 1812.0 (2018-06-14) CGP — 890.4 (2018-06-14) IQN — 29091.0 (2018-06-14) A2C + SIL — 1812.0 (2018-06-14) CGP — 890.4 (2018-06-14) POP3D — 5400.13 (2018-07-02) POP3D — 5400.13 (2018-07-02) R2D2 — 108197.0 (2019-05-01) R2D2 — 108197.0 (2019-05-01) SAC — 350.0 (2019-10-16) SAC — 350.0 (2019-10-16) MuZero — 143972.03 (2019-11-19) MuZero — 143972.03 (2019-11-19) Agent57 — 67212.67 (2020-03-30) Agent57 — 67212.67 (2020-03-30) CURL — 543.7 (2020-04-08) CURL — 543.7 (2020-04-08) DreamerV2 — 23625.0 (2020-10-05) DreamerV2 — 23625.0 (2020-10-05) MuZero (Res2 Adam) — 33292.22 (2021-04-13) MuZero (Res2 Adam) — 33292.22 (2021-04-13) GDI-H3 — 97155.0 (2022-06-07) GDI-I3 — 63876.0 (2022-06-07) GDI-H3 — 97155.0 (2022-06-07) GDI-I3 — 63876.0 (2022-06-07) DNA — 16293.0 (2022-06-20) DNA — 16293.0 (2022-06-20) ASL DDQN — 14372.8 (2023-05-07) ASL DDQN — 14372.8 (2023-05-07) UCT — 1512.2 (2012-07-19) Nature DQN — 3359.0 (2015-02-25) Prior+Duel hs — 10950.6 (2015-09-22) Prior+Duel noop — 11477.0 (2015-11-20) A3C LSTM hs — 14497.9 (2016-02-04) QR-DQN-1 — 22012.0 (2017-10-27) Ape-X — 24559.4 (2018-03-02) IQN — 29091.0 (2018-06-14) R2D2 — 108197.0 (2019-05-01) MuZero — 143972.03 (2019-11-19)
RankModel Score PaperCodeYear
1 MuZero 143972.03 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
2 R2D2 108197.0 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
3 GDI-H3 97155 Generalized Data Distribution Iteration 2022
4 Agent57 67212.67 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
5 GDI-I3 63876 Generalized Data Distribution Iteration 2022
6 MuZero (Res2 Adam) 33292.22 Online and Offline Reinforcement Learning by Planning with a Learned Model DHDev0/Muzero-unplugged · enpasos/muzero 2021
7 IQN 29091 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
8 Ape-X 24559.4 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
9 DreamerV2 23625 Mastering Atari with Discrete World Models opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6 2020
10 QR-DQN-1 22012 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
11 IMPALA (deep) 19148.47 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
12 DNA 16293 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
13 A3C LSTM hs 14497.9 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
14 ASL DDQN 14372.8 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
15 Prior+Duel noop 11477.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
16 NoisyNet-Dueling 11231 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
17 Prior+Duel hs 10950.6 Deep Reinforcement Learning with Double Q-learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94 2015
17 Prior+Duel hs 10950.6 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
19 DDQN+Pop-Art noop 9011.6 Learning values across many orders of magnitude 2016
20 Reactor 500M 8323.3 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
1–20 / 90 다음 → 페이지당 10 20 50 100