Atari Games on Atari 2600 Berzerk

78개 결과 · ⬇ CSV · JSON

Score

Rank	Model	Score	Paper	Code	Year
1	Go-Explore	197376	First return, then explore	uber-research/go-explore · qgallouedec/lge	2020
2	MuZero	85932.60	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15	2019
3	Agent57	61507.83	Agent57: Outperforming the Atari Human Benchmark	michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2	2020
4	Ape-X	57196.7	Distributed Prioritized Experience Replay	ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12	2018
5	R2D2	53318.7	Recurrent Experience Replay in Distributed Reinforcement Learning	opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl	2019
6	DNA	19789	DNA: Proximal Policy Optimization with a Dual Network Architecture	maitchison/PPO	2022
7	GDI-H3	14649	Generalized Data Distribution Iteration		2022
8	FQF	12422.2	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3	2019
9	GDI-I3	7607	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning		2021
9	GDI-I3	7607	Generalized Data Distribution Iteration		2022
11	Prior+Duel noop	3409.0	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
12	QR-DQN-1	3117	Distributional Reinforcement Learning with Quantile Regression	DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14	2017
13	MuZero (Res2 Adam)	2705.82	Online and Offline Reinforcement Learning by Planning with a Learned Model	DHDev0/Muzero-unplugged · enpasos/muzero	2021
14	ASL DDQN	2597.2	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	xinjinghao/color	2023
15	Reactor 500M	2303.1	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning		2017
16	Prior+Duel hs	2178.6	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
17	NoisyNet-Dueling	1896	Noisy Networks for Exploration	opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12	2017
18	IMPALA (deep)	1852.70	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21	2018
19	C51 noop	1645.0	A Distributional Perspective on Reinforcement Learning	facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19	2017
20	Duel noop	1472.6	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
21	A3C FF (1 day) hs	1433.4	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
22	Persistent AL	1328.25	Increasing the Action Gap: New Operators for Reinforcement Learning	janhuenermann/neurojs · chainer/chainerrl	2015
23	Prior noop	1305.6	Prioritized Experience Replay	labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74	2015
24	DDQN (tuned) noop	1225.4	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
25	DDQN+Pop-Art noop	1199.6	Learning values across many orders of magnitude		2016
26	CGP	1138	Evolving simple programs for playing Atari games	ShuhuaGao/gpFlappyBird · JacobLaney/cgp-tetris	2018
27	IQN	1053	Implicit Quantile Networks for Distributional Reinforcement Learning	opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16	2018
28	DDQN (tuned) hs	1011.1	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
29	Duel hs	910.6	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
30	Prior hs	865.9	Prioritized Experience Replay	labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74	2015
31	A3C LSTM hs	862.2	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
32	A3C FF hs	817.9	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
33	DreamerV2	810	Mastering Atari with Discrete World Models	opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6	2020
34	Advantage Learning	747.26	Increasing the Action Gap: New Operators for Reinforcement Learning	janhuenermann/neurojs · chainer/chainerrl	2015
35	ES FF (1 hour) noop	686.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	ray-project/ray · openai/evolution-strategies-starter · atgambardella/pytorch-es · +20	2017
36	Best Baseline	670	The Arcade Learning Environment: An Evaluation Platform for General Agents	mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory	2012
37	DQN noop	585.6	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
38	Best Learner	501.3	The Arcade Learning Environment: An Evaluation Platform for General Agents	mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory	2012
39	DQN hs	493.4	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
40	Go-Explore	197376	First return, then explore	uber-research/go-explore · qgallouedec/lge	2020
41	MuZero	85932.60	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15	2019
42	Agent57	61507.83	Agent57: Outperforming the Atari Human Benchmark	michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2	2020
43	Ape-X	57196.7	Distributed Prioritized Experience Replay	ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12	2018
44	R2D2	53318.7	Recurrent Experience Replay in Distributed Reinforcement Learning	opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl	2019
45	DNA	19789	DNA: Proximal Policy Optimization with a Dual Network Architecture	maitchison/PPO	2022
46	GDI-H3	14649	Generalized Data Distribution Iteration		2022
47	FQF	12422.2	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3	2019
48	GDI-I3	7607	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning		2021
48	GDI-I3	7607	Generalized Data Distribution Iteration		2022
50	Prior+Duel noop	3409.0	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
51	QR-DQN-1	3117	Distributional Reinforcement Learning with Quantile Regression	DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14	2017
52	MuZero (Res2 Adam)	2705.82	Online and Offline Reinforcement Learning by Planning with a Learned Model	DHDev0/Muzero-unplugged · enpasos/muzero	2021
53	ASL DDQN	2597.2	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	xinjinghao/color	2023
54	Reactor 500M	2303.1	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning		2017
55	Prior+Duel hs	2178.6	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
56	NoisyNet-Dueling	1896	Noisy Networks for Exploration	opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12	2017
57	IMPALA (deep)	1852.70	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21	2018
58	C51 noop	1645.0	A Distributional Perspective on Reinforcement Learning	facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19	2017
59	Duel noop	1472.6	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
60	A3C FF (1 day) hs	1433.4	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
61	Persistent AL	1328.25	Increasing the Action Gap: New Operators for Reinforcement Learning	janhuenermann/neurojs · chainer/chainerrl	2015
62	Prior noop	1305.6	Prioritized Experience Replay	labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74	2015
63	DDQN (tuned) noop	1225.4	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
64	DDQN+Pop-Art noop	1199.6	Learning values across many orders of magnitude		2016
65	CGP	1138	Evolving simple programs for playing Atari games	ShuhuaGao/gpFlappyBird · JacobLaney/cgp-tetris	2018
66	IQN	1053	Implicit Quantile Networks for Distributional Reinforcement Learning	opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16	2018
67	DDQN (tuned) hs	1011.1	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
68	Duel hs	910.6	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
69	Prior hs	865.9	Prioritized Experience Replay	labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74	2015
70	A3C LSTM hs	862.2	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
71	A3C FF hs	817.9	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
72	DreamerV2	810	Mastering Atari with Discrete World Models	opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6	2020
73	Advantage Learning	747.26	Increasing the Action Gap: New Operators for Reinforcement Learning	janhuenermann/neurojs · chainer/chainerrl	2015
74	ES FF (1 hour) noop	686.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	ray-project/ray · openai/evolution-strategies-starter · atgambardella/pytorch-es · +20	2017
75	Best Baseline	670	The Arcade Learning Environment: An Evaluation Platform for General Agents	mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory	2012
76	DQN noop	585.6	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
77	Best Learner	501.3	The Arcade Learning Environment: An Evaluation Platform for General Agents	mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory	2012
78	DQN hs	493.4	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015