Atari Games on Atari 2600 Montezuma's Revenge

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Go-Explore	43791	No	First return, then explore	2020-04-27	Code
2	Go-Explore	43763	No	Go-Explore: a New Approach for Hard-Exploration ...	2019-01-30	Code
3	SND-V	21565	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
4	Agent57	9352.01	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	RND	8152	No	Exploration by Random Network Distillation	2018-10-30	Code
6	SND-VIC	7838	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
7	SND-STD	7212	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
8	A2C+CoEX	6635	No	Contingency-Aware Exploration in Reinforcement L...	2018-11-05	-
9	DQN-PixelCNN	3705.5	No	Count-Based Exploration with Neural Density Models	2017-03-03	Code
10	DDQN-PC	3459	No	Unifying Count-Based Exploration and Intrinsic M...	2016-06-06	Code
11	GDI-I3	3000	No	Generalized Data Distribution Iteration	2022-06-07	-
12	GDI-I3	3000	No	Generalized Data Distribution Iteration	2022-06-07	-
13	Sarsa-φ-EB	2745.4	No	Count-Based Exploration in Feature Space for Rei...	2017-06-25	Code
14	Intrinsic Reward Agent	2504.6	No	Large-Scale Study of Curiosity-Driven Learning	2018-08-13	Code
15	Ape-X	2500	No	Distributed Prioritized Experience Replay	2018-03-02	Code
16	MuZero (Res2 Adam)	2500	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
17	GDI-H3	2500	No	Generalized Data Distribution Iteration	2022-06-07	-
18	R2D2	2061.3	No	-	-	Code
19	DQN+SR	1778.8	No	Count-Based Exploration with the Successor Repre...	2018-07-31	Code
20	DQNMMCe+SR	1778.6	No	Count-Based Exploration with the Successor Repre...	2018-07-31	Code
21	A2C + SIL	1100	No	Self-Imitation Learning	2018-06-14	Code
22	Sarsa-ε	399.5	No	Count-Based Exploration in Feature Space for Rei...	2017-06-25	Code
23	A3C-CTS	273.7	No	Unifying Count-Based Exploration and Intrinsic M...	2016-06-06	Code
24	SARSA	259	No	-	-	-
25	MP-EB	142	No	Incentivizing Exploration In Reinforcement Learn...	2015-07-03	Code
26	Bootstrapped DQN	100	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
27	Gorila	84	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
28	DreamerV2	81	No	Mastering Atari with Discrete World Models	2020-10-05	Code
29	TRPO-hash	75	No	#Exploration: A Study of Count-Based Exploration...	2016-11-15	Code
30	A3C FF hs	67	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
31	NoisyNet-Dueling	57	No	Noisy Networks for Exploration	2017-06-30	Code
32	A3C FF (1 day) hs	53	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
33	Prior hs	51	No	Prioritized Experience Replay	2015-11-18	Code
34	DQN hs	47	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	DDQN (tuned) hs	42	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
36	A3C LSTM hs	41	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
37	Prior+Duel hs	24	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	Duel hs	22	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
39	Best Learner	10.7	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
40	Persistent AL	1.72	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
41	Advantage Learning	0.42	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
42	IQN	0	No	-	-	Code
43	MuZero	0	No	-	-	Code
44	IMPALA (deep)	0	No	-	-	Code
45	CGP	0	No	-	-	Code
46	POP3D	0	No	-	-	Code
47	QR-DQN-1	0	No	-	-	Code
48	DNA	0	No	-	-	Code
49	ASL DDQN	0	No	-	-	Code
50	Nature DQN	0	No	-	-	Code

#1Go-ExploreSOTA
43791
Score· 2020-04-27
First return, then explore Code
#2Go-ExploreSOTA
43763
Score· 2019-01-30
Go-Explore: a New Approach for Hard-Exploration Problems Code
#3SND-V
21565
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#4Agent57
9352.01
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#5RNDSOTA
8152
Score· 2018-10-30
Exploration by Random Network Distillation Code
#6SND-VIC
7838
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#7SND-STD
7212
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#8A2C+CoEX
6635
Score· 2018-11-05
Contingency-Aware Exploration in Reinforcement Learning
#9DQN-PixelCNNSOTA
3705.5
Score· 2017-03-03
Count-Based Exploration with Neural Density Models Code
#10DDQN-PCSOTA
3459
Score· 2016-06-06
Unifying Count-Based Exploration and Intrinsic Motivation Code
#11GDI-I3
3000
Score· 2022-06-07
Generalized Data Distribution Iteration
#12GDI-I3
3000
Score· 2022-06-07
Generalized Data Distribution Iteration
#13Sarsa-φ-EB
2745.4
Score· 2017-06-25
Count-Based Exploration in Feature Space for Reinforcement Learning Code
#14Intrinsic Reward Agent
2504.6
Score· 2018-08-13
Large-Scale Study of Curiosity-Driven Learning Code
#15Ape-X
2500
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#16MuZero (Res2 Adam)
2500
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#17GDI-H3
2500
Score· 2022-06-07
Generalized Data Distribution Iteration
#18R2D2
2061.3
Score
No paperCode
#19DQN+SR
1778.8
Score· 2018-07-31
Count-Based Exploration with the Successor Representation Code
#20DQNMMCe+SR
1778.6
Score· 2018-07-31
Count-Based Exploration with the Successor Representation Code
#21A2C + SIL
1100
Score· 2018-06-14
Self-Imitation Learning Code
#22Sarsa-ε
399.5
Score· 2017-06-25
Count-Based Exploration in Feature Space for Reinforcement Learning Code
#23A3C-CTS
273.7
Score· 2016-06-06
Unifying Count-Based Exploration and Intrinsic Motivation Code
#24SARSA
259
Score
No paper
#25MP-EBSOTA
142
Score· 2015-07-03
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models Code
#26Bootstrapped DQN
100
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#27Gorila
84
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#28DreamerV2
81
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#29TRPO-hash
75
Score· 2016-11-15
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning Code
#30A3C FF hs
67
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#31NoisyNet-Dueling
57
Score· 2017-06-30
Noisy Networks for Exploration Code
#32A3C FF (1 day) hs
53
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#33Prior hs
51
Score· 2015-11-18
Prioritized Experience Replay Code
#34DQN hs
47
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35DDQN (tuned) hs
42
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#36A3C LSTM hs
41
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#37Prior+Duel hs
24
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38Duel hs
22
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#39Best LearnerSOTA
10.7
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#40Persistent AL
1.72
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#41Advantage Learning
0.42
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#42IQN
0
Score
No paperCode
#43MuZero
0
Score
No paperCode
#44IMPALA (deep)
0
Score
No paperCode
#45CGP
0
Score
No paperCode
#46POP3D
0
Score
No paperCode
#47QR-DQN-1
0
Score
No paperCode
#48DNA
0
Score
No paperCode
#49ASL DDQN
0
Score
No paperCode
#50Nature DQN
0
Score
No paperCode