Video Games on Atari 2600 Private Eye

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Go-Explore	95756	No	First return, then explore	2020-04-27	Code
2	Agent57	79716.46	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
3	SND-VIC	17313	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
4	MuZero	15299.98	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
5	GDI-I3	15100	No	Generalized Data Distribution Iteration	2022-06-07	-
6	GDI-I3	15100	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-H3	15100	No	Generalized Data Distribution Iteration	2022-06-07	-
8	C51 noop	15095	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
9	SND-STD	15089	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
10	CGP	12702.2	No	Evolving simple programs for playing Atari games	2018-06-14	Code
11	RND	8666	No	Exploration by Random Network Distillation	2018-10-30	Code
12	DQN-PixelCNN	8358.7	No	Count-Based Exploration with Neural Density Models	2017-03-03	Code
13	R2D2	5322.7	No	-	-	Code
14	Advantage Learning	5276.16	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
15	SND-V	4213	No	Self-supervised network distillation: an effecti...	2023-02-22	Code
16	Intrinsic Reward Agent	3036.5	No	Large-Scale Study of Curiosity-Driven Learning	2018-08-13	Code
17	Gorila	2598.6	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
18	DreamerV2	2198	No	Mastering Atari with Discrete World Models	2020-10-05	Code
19	Best Baseline	1947.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
20	Bootstrapped DQN	1812.5	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
21	Nature DQN	1788	No	-	-	Code
22	Prior+Duel hs	1277.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
23	Best Learner	684.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
24	Prior hs	670.7	No	Prioritized Experience Replay	2015-11-18	Code
25	A2C + SIL	661.2	No	Self-Imitation Learning	2018-06-14	Code
26	A3C LSTM hs	421.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
27	QR-DQN-1	350	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
28	ASL DDQN	349.7	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
29	Duel hs	292.6	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
30	DDQN+Pop-Art noop	286.7	No	Learning values across many orders of magnitude	2016-02-24	-
31	NoisyNet-Dueling	279	No	Noisy Networks for Exploration	2017-06-30	Code
32	DQN hs	207.9	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	A3C FF hs	206.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
34	Prior+Duel noop	206	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
35	DQN-CTS	206	No	Count-Based Exploration with Neural Density Models	2017-03-03	Code
36	Prior noop	200	No	Prioritized Experience Replay	2015-11-18	Code
37	IQN	200	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
38	A3C FF (1 day) hs	194.4	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
39	DQN noop	146.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
40	DDQN (tuned) noop	129.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
41	CURL	105.2	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
42	Duel noop	103	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
43	ES FF (1 hour) noop	100	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
44	MuZero (Res2 Adam)	100	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
45	DNA	100	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
46	A3C-CTS	99.32	No	Unifying Count-Based Exploration and Intrinsic M...	2016-06-06	Code
47	DQNMMCe+SR	99.1	No	Count-Based Exploration with the Successor Repre...	2018-07-31	Code
48	IMPALA (deep)	98.5	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
49	SARSA	86	No	-	-	-
50	POP3D	79.67	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
51	Ape-X	49.8	No	Distributed Prioritized Experience Replay	2018-03-02	Code
52	DDQN (tuned) hs	-575.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code

#1Go-ExploreSOTA
95756
Score· 2020-04-27
First return, then explore Code
#2Agent57SOTA
79716.46
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#3SND-VIC
17313
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#4MuZeroSOTA
15299.98
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#5GDI-I3
15100
Score· 2022-06-07
Generalized Data Distribution Iteration
#6GDI-I3
15100
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-H3
15100
Score· 2022-06-07
Generalized Data Distribution Iteration
#8C51 noopSOTA
15095
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#9SND-STD
15089
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#10CGP
12702.2
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#11RND
8666
Score· 2018-10-30
Exploration by Random Network Distillation Code
#12DQN-PixelCNNSOTA
8358.7
Score· 2017-03-03
Count-Based Exploration with Neural Density Models Code
#13R2D2
5322.7
Score
No paperCode
#14Advantage LearningSOTA
5276.16
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#15SND-V
4213
Score· 2023-02-22
Self-supervised network distillation: an effective approach to exploration in sparse reward environments Code
#16Intrinsic Reward Agent
3036.5
Score· 2018-08-13
Large-Scale Study of Curiosity-Driven Learning Code
#17GorilaSOTA
2598.6
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#18DreamerV2
2198
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#19Best BaselineSOTA
1947.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#20Bootstrapped DQN
1812.5
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#21Nature DQN
1788
Score
No paperCode
#22Prior+Duel hs
1277.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#23Best Learner
684.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#24Prior hs
670.7
Score· 2015-11-18
Prioritized Experience Replay Code
#25A2C + SIL
661.2
Score· 2018-06-14
Self-Imitation Learning Code
#26A3C LSTM hs
421.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#27QR-DQN-1
350
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#28ASL DDQN
349.7
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#29Duel hs
292.6
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#30DDQN+Pop-Art noop
286.7
Score· 2016-02-24
Learning values across many orders of magnitude
#31NoisyNet-Dueling
279
Score· 2017-06-30
Noisy Networks for Exploration Code
#32DQN hs
207.9
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33A3C FF hs
206.9
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#34Prior+Duel noop
206
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#35DQN-CTS
206
Score· 2017-03-03
Count-Based Exploration with Neural Density Models Code
#36Prior noop
200
Score· 2015-11-18
Prioritized Experience Replay Code
#37IQN
200
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#38A3C FF (1 day) hs
194.4
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#39DQN noop
146.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#40DDQN (tuned) noop
129.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#41CURL
105.2
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#42Duel noop
103
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#43ES FF (1 hour) noop
100
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#44MuZero (Res2 Adam)
100
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#45DNA
100
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#46A3C-CTS
99.32
Score· 2016-06-06
Unifying Count-Based Exploration and Intrinsic Motivation Code
#47DQNMMCe+SR
99.1
Score· 2018-07-31
Count-Based Exploration with the Successor Representation Code
#48IMPALA (deep)
98.5
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#49SARSA
86
Score
No paper
#50POP3D
79.67
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#51Ape-X
49.8
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#52DDQN (tuned) hs
-575.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code