Atari Games on Atari 2600 Star Gunner

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Agent57	839573.53	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
2	R2D2	717344	No	-	-	Code
3	GDI-H3	677590	No	Generalized Data Distribution Iteration	2022-06-07	-
4	MuZero	549271.7	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
5	GDI-I3	465750	No	Generalized Data Distribution Iteration	2022-06-07	-
6	GDI-I3	465750	No	Generalized Data Distribution Iteration	2022-06-07	-
7	Ape-X	434342.5	No	Distributed Prioritized Experience Replay	2018-03-02	Code
8	IMPALA (deep)	200625	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
9	A3C LSTM hs	164766	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
10	MuZero (Res2 Adam)	154548.26	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
11	A3C FF hs	138218	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
12	FQF	131981.2	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
13	ASL DDQN	129140	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
14	Prior+Duel hs	127073	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
15	Prior+Duel noop	125117	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
16	DNA	104125	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
17	Duel hs	90804	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	Duel noop	89238	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
19	QR-DQN-1	77495	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
20	NoisyNet-Dueling	75867	No	Noisy Networks for Exploration	2017-06-30	Code
21	IQN	74677	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
22	RIMs-PPO	70000	No	-	-	-
23	A3C FF (1 day) hs	64393	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
24	Prior noop	63302	No	Prioritized Experience Replay	2015-11-18	Code
25	Prior hs	61582	No	Prioritized Experience Replay	2015-11-18	Code
26	Advantage Learning	61353.59	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
27	DDQN (tuned) noop	60142	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
28	DDQN (tuned) hs	58365	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
29	Nature DQN	57997	No	-	-	Code
30	Bootstrapped DQN	55725	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
31	DQN noop	54282	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	DQN hs	52970	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	C51 noop	49095	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
34	POP3D	48984	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
35	A2C + SIL	31309.2	No	Self-Imitation Learning	2018-06-14	Code
36	Gorila	14919.2	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
37	DreamerV2	7800	No	Mastering Atari with Discrete World Models	2020-10-05	Code
38	CGP	2320	No	Evolving simple programs for playing Atari games	2018-06-14	Code
39	ES FF (1 hour) noop	1470	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
40	Full Tree	1345	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
41	Best Learner	1069.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	DDQN+Pop-Art noop	589	No	Learning values across many orders of magnitude	2016-02-24	-
43	SARSA	9.4	No	-	-	Code

#1Agent57SOTA
839573.53
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#2R2D2
717344
Score
No paperCode
#3GDI-H3
677590
Score· 2022-06-07
Generalized Data Distribution Iteration
#4MuZeroSOTA
549271.7
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#5GDI-I3
465750
Score· 2022-06-07
Generalized Data Distribution Iteration
#6GDI-I3
465750
Score· 2022-06-07
Generalized Data Distribution Iteration
#7Ape-XSOTA
434342.5
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#8IMPALA (deep)SOTA
200625
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#9A3C LSTM hsSOTA
164766
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#10MuZero (Res2 Adam)
154548.26
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#11A3C FF hs
138218
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#12FQF
131981.2
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#13ASL DDQN
129140
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#14Prior+Duel hsSOTA
127073
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#15Prior+Duel noop
125117
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#16DNA
104125
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#17Duel hs
90804
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18Duel noop
89238
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#19QR-DQN-1
77495
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#20NoisyNet-Dueling
75867
Score· 2017-06-30
Noisy Networks for Exploration Code
#21IQN
74677
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#22RIMs-PPO
70000
Score
No paper
#23A3C FF (1 day) hs
64393
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#24Prior noop
63302
Score· 2015-11-18
Prioritized Experience Replay Code
#25Prior hs
61582
Score· 2015-11-18
Prioritized Experience Replay Code
#26Advantage Learning
61353.59
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#27DDQN (tuned) noop
60142
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#28DDQN (tuned) hs
58365
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#29Nature DQN
57997
Score
No paperCode
#30Bootstrapped DQN
55725
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#31DQN noop
54282
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32DQN hs
52970
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33C51 noop
49095
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#34POP3D
48984
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#35A2C + SIL
31309.2
Score· 2018-06-14
Self-Imitation Learning Code
#36GorilaSOTA
14919.2
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#37DreamerV2
7800
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#38CGP
2320
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#39ES FF (1 hour) noop
1470
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#40Full TreeSOTA
1345
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#41Best Learner
1069.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#42DDQN+Pop-Art noop
589
Score· 2016-02-24
Learning values across many orders of magnitude
#43SARSA
9.4
Score
No paperCode