paper-with-me

Atari Games 벤치마크

Atari Games on Atari 2600 Chopper Command

90개 결과 · ⬇ CSV · JSON

Score

775 2.506e+05 5.004e+05 7.502e+05 1e+06 2012-07 2026-11 UCT — 34018.8 (2012-07-19) Best Learner — 1581.5 (2012-07-19) UCT — 34018.8 (2012-07-19) Best Learner — 1581.5 (2012-07-19) Nature DQN — 6687.0 (2015-02-25) Nature DQN — 6687.0 (2015-02-25) Gorila — 3191.8 (2015-07-15) Gorila — 3191.8 (2015-07-15) Prior+Duel hs — 8058.0 (2015-09-22) DQN noop — 6126.0 (2015-09-22) DQN hs — 5017.0 (2015-09-22) DDQN (tuned) hs — 3495.0 (2015-09-22) Prior+Duel hs — 8058.0 (2015-09-22) DQN noop — 6126.0 (2015-09-22) DQN hs — 5017.0 (2015-09-22) DDQN (tuned) hs — 3495.0 (2015-09-22) Prior noop — 8600.0 (2015-11-18) Prior hs — 4635.0 (2015-11-18) Prior noop — 8600.0 (2015-11-18) Prior hs — 4635.0 (2015-11-18) Prior+Duel noop — 13185.0 (2015-11-20) Duel noop — 11215.0 (2015-11-20) DDQN (tuned) noop — 5809.0 (2015-11-20) Duel hs — 3784.0 (2015-11-20) Prior+Duel noop — 13185.0 (2015-11-20) Duel noop — 11215.0 (2015-11-20) DDQN (tuned) noop — 5809.0 (2015-11-20) Duel hs — 3784.0 (2015-11-20) Persistent AL — 5734.93 (2015-12-15) Advantage Learning — 5431.36 (2015-12-15) Persistent AL — 5734.93 (2015-12-15) Advantage Learning — 5431.36 (2015-12-15) A3C LSTM hs — 10150.0 (2016-02-04) A3C FF hs — 7021.0 (2016-02-04) A3C FF (1 day) hs — 4669.0 (2016-02-04) A3C LSTM hs — 10150.0 (2016-02-04) A3C FF hs — 7021.0 (2016-02-04) A3C FF (1 day) hs — 4669.0 (2016-02-04) Bootstrapped DQN — 4100.0 (2016-02-15) Bootstrapped DQN — 4100.0 (2016-02-15) DDQN+Pop-Art noop — 775.0 (2016-02-24) DDQN+Pop-Art noop — 775.0 (2016-02-24) ES FF (1 hour) noop — 3710.0 (2017-03-10) ES FF (1 hour) noop — 3710.0 (2017-03-10) Reactor 500M — 107779.0 (2017-04-15) Reactor 500M — 107779.0 (2017-04-15) NoisyNet-Dueling — 11477.0 (2017-06-30) NoisyNet-Dueling — 11477.0 (2017-06-30) C51 noop — 15600.0 (2017-07-21) C51 noop — 15600.0 (2017-07-21) QR-DQN-1 — 14667.0 (2017-10-27) QR-DQN-1 — 14667.0 (2017-10-27) IMPALA (deep) — 28255.0 (2018-02-05) IMPALA (deep) — 28255.0 (2018-02-05) Ape-X — 721851.0 (2018-03-02) Ape-X — 721851.0 (2018-03-02) IQN — 16836.0 (2018-06-14) A2C + SIL — 6710.0 (2018-06-14) CGP — 3580.0 (2018-06-14) IQN — 16836.0 (2018-06-14) A2C + SIL — 6710.0 (2018-06-14) CGP — 3580.0 (2018-06-14) POP3D — 6308.33 (2018-07-02) POP3D — 6308.33 (2018-07-02) R2D2 — 986652.0 (2019-05-01) R2D2 — 986652.0 (2019-05-01) FQF — 876460.0 (2019-11-05) FQF — 876460.0 (2019-11-05) MuZero — 991039.7 (2019-11-19) MuZero — 991039.7 (2019-11-19) Agent57 — 999900.0 (2020-03-30) Agent57 — 999900.0 (2020-03-30) CURL — 1198.0 (2020-04-08) CURL — 1198.0 (2020-04-08) DreamerV2 — 2861.0 (2020-10-05) DreamerV2 — 2861.0 (2020-10-05) MuZero (Res2 Adam) — 5989.55 (2021-04-13) MuZero (Res2 Adam) — 5989.55 (2021-04-13) GDI-H3 — 999999.0 (2021-06-11) GDI-H3 — 999999.0 (2021-06-11) GDI-I3 — 999999.0 (2022-06-07) GDI-H3 — 999999.0 (2022-06-07) GDI-I3 — 999999.0 (2022-06-07) GDI-H3 — 999999.0 (2022-06-07) DNA — 31181.0 (2022-06-20) DNA — 31181.0 (2022-06-20) ASL DDQN — 15071.0 (2023-05-07) ASL DDQN — 15071.0 (2023-05-07) UCT — 34018.8 (2012-07-19) Reactor 500M — 107779.0 (2017-04-15) Ape-X — 721851.0 (2018-03-02) R2D2 — 986652.0 (2019-05-01) MuZero — 991039.7 (2019-11-19) Agent57 — 999900.0 (2020-03-30) GDI-H3 — 999999.0 (2021-06-11)
RankModel Score PaperCodeYear
1 GDI-H3 999999 GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 2021
1 GDI-I3 999999 Generalized Data Distribution Iteration 2022
1 GDI-H3 999999 Generalized Data Distribution Iteration 2022
4 Agent57 999900 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
5 MuZero 991039.70 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 986652.0 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
7 FQF 876460.0 Fully Parameterized Quantile Function for Distributional Reinforcement Learning opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3 2019
8 Ape-X 721851 Distributed Prioritized Experience Replay ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12 2018
9 Reactor 500M 107779.0 The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 2017
10 UCT 34018.8 The Arcade Learning Environment: An Evaluation Platform for General Agents mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory 2012
11 DNA 31181 DNA: Proximal Policy Optimization with a Dual Network Architecture maitchison/PPO 2022
12 IMPALA (deep) 28255.00 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21 2018
13 IQN 16836 Implicit Quantile Networks for Distributional Reinforcement Learning opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16 2018
14 C51 noop 15600.0 A Distributional Perspective on Reinforcement Learning facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19 2017
15 ASL DDQN 15071 Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity xinjinghao/color 2023
16 QR-DQN-1 14667 Distributional Reinforcement Learning with Quantile Regression DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14 2017
17 Prior+Duel noop 13185.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
18 NoisyNet-Dueling 11477 Noisy Networks for Exploration opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12 2017
19 Duel noop 11215.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70 2015
20 A3C LSTM hs 10150.0 Asynchronous Methods for Deep Reinforcement Learning ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67 2016
1–20 / 90 다음 → 페이지당 10 20 50 100