Atari Games on Atari 2600 Venture

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Agent57	2623.71	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
2	Go-Explore	2281	No	First return, then explore	2020-04-27	Code
3	SND-VIC	2188	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
4	SND-STD	2138	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
5	GDI-I3	2035	No	Generalized Data Distribution Iteration	2022-06-07	-
6	GDI-H3(200M frames)	2000	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-H3	2000	No	Generalized Data Distribution Iteration	2022-06-07	-
8	R2D2	1970.7	No	-	-	Code
9	RND	1859	No	Exploration by Random Network Distillation	2018-10-30	Code
10	Ape-X	1813	No	Distributed Prioritized Experience Replay	2018-03-02	Code
11	SND-V	1787	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
12	MuZero (Res2 Adam)	1731.47	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
13	C51 noop	1520	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
14	RUDDER	1350	No	RUDDER: Return Decomposition for Delayed Rewards	2018-06-20	Code
15	IQN	1318	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
16	DQNMMCe+SR	1241.8	No	Count-Based Exploration with the Successor Repre...	2018-07-31	Code
17	DDQN+Pop-Art noop	1172	No	Learning values across many orders of magnitude	2016-02-24	-
18	Sarsa-φ-EB	1169.2	No	Count-Based Exploration in Feature Space for Rei...	2017-06-25	Code
19	NoisyNet-Dueling	815	No	Noisy Networks for Exploration	2017-06-30	Code
20	ES FF (1 hour) noop	760	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
21	Gorila	523.4	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
22	Duel noop	497	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
23	TRPO-hash	445	No	#Exploration: A Study of Count-Based Exploration...	2016-11-15	Code
24	Intrinsic Reward Agent	416	No	Large-Scale Study of Curiosity-Driven Learning	2018-08-13	Code
25	Nature DQN	380	No	-	-	Code
26	ASL DDQN	291	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
27	Bootstrapped DQN	212.5	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
28	Duel hs	200	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
29	Advantage Learning	198.69	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
30	DQN noop	163	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
31	DQN hs	136	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	DDQN (tuned) noop	98	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
33	Prior hs	94	No	Prioritized Experience Replay	2015-11-18	Code
34	DQN-PixelCNN	82.2	No	Count-Based Exploration with Neural Density Models	2017-03-03	Code
35	Best Learner	66	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
36	Prior noop	54	No	Prioritized Experience Replay	2015-11-18	Code
37	Prior+Duel noop	48	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
38	DQN-CTS	48	No	Count-Based Exploration with Neural Density Models	2017-03-03	Code
39	QR-DQN-1	43.9	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
40	POP3D	36.33	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
41	Prior+Duel hs	29	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
42	A3C LSTM hs	25	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
43	A3C FF hs	23	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
44	DDQN (tuned) hs	21	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
45	A3C FF (1 day) hs	19	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
46	DreamerV2	2	No	Mastering Atari with Discrete World Models	2020-10-05	Code
47	SARSA	0.6	No	-	-	-
48	MuZero	0.4	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
49	MP-EB	0	No	-	-	Code
50	A3C-CTS	0	No	-	-	Code
51	Sarsa-ε	0	No	-	-	Code
52	IMPALA (deep)	0	No	-	-	Code
53	A2C + SIL	0	No	-	-	Code
54	CGP	0	No	-	-	Code
55	DNA	0	No	-	-	Code

#1Agent57SOTA
2623.71
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#2Go-Explore
2281
Score· 2020-04-27
First return, then explore Code
#3SND-VIC
2188
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#4SND-STD
2138
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#5GDI-I3
2035
Score· 2022-06-07
Generalized Data Distribution Iteration
#6GDI-H3(200M frames)
2000
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-H3
2000
Score· 2022-06-07
Generalized Data Distribution Iteration
#8R2D2
1970.7
Score
No paperCode
#9RNDSOTA
1859
Score· 2018-10-30
Exploration by Random Network Distillation Code
#10Ape-XSOTA
1813
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#11SND-V
1787
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#12MuZero (Res2 Adam)
1731.47
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#13C51 noopSOTA
1520
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#14RUDDER
1350
Score· 2018-06-20
RUDDER: Return Decomposition for Delayed Rewards Code
#15IQN
1318
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#16DQNMMCe+SR
1241.8
Score· 2018-07-31
Count-Based Exploration with the Successor Representation Code
#17DDQN+Pop-Art noopSOTA
1172
Score· 2016-02-24
Learning values across many orders of magnitude
#18Sarsa-φ-EB
1169.2
Score· 2017-06-25
Count-Based Exploration in Feature Space for Reinforcement Learning Code
#19NoisyNet-Dueling
815
Score· 2017-06-30
Noisy Networks for Exploration Code
#20ES FF (1 hour) noop
760
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#21GorilaSOTA
523.4
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#22Duel noop
497
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#23TRPO-hash
445
Score· 2016-11-15
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning Code
#24Intrinsic Reward Agent
416
Score· 2018-08-13
Large-Scale Study of Curiosity-Driven Learning Code
#25Nature DQN
380
Score
No paperCode
#26ASL DDQN
291
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#27Bootstrapped DQN
212.5
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#28Duel hs
200
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#29Advantage Learning
198.69
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#30DQN noop
163
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#31DQN hs
136
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32DDQN (tuned) noop
98
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#33Prior hs
94
Score· 2015-11-18
Prioritized Experience Replay Code
#34DQN-PixelCNN
82.2
Score· 2017-03-03
Count-Based Exploration with Neural Density Models Code
#35Best LearnerSOTA
66
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#36Prior noop
54
Score· 2015-11-18
Prioritized Experience Replay Code
#37Prior+Duel noop
48
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#38DQN-CTS
48
Score· 2017-03-03
Count-Based Exploration with Neural Density Models Code
#39QR-DQN-1
43.9
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#40POP3D
36.33
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#41Prior+Duel hs
29
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#42A3C LSTM hs
25
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#43A3C FF hs
23
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#44DDQN (tuned) hs
21
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#45A3C FF (1 day) hs
19
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#46DreamerV2
2
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#47SARSA
0.6
Score
No paper
#48MuZero
0.4
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#49MP-EB
0
Score
No paperCode
#50A3C-CTS
0
Score
No paperCode
#51Sarsa-ε
0
Score
No paperCode
#52IMPALA (deep)
0
Score
No paperCode
#53A2C + SIL
0
Score
No paperCode
#54CGP
0
Score
No paperCode
#55DNA
0
Score
No paperCode