Atari Games on Atari 2600 Space Invaders

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3(200M frames)	154380	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-H3	154380	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-I3	140460	No	GDI: Rethinking What Makes Reinforcement Learnin...	2021-06-11	-
4	GDI-I3	140460	No	GDI: Rethinking What Makes Reinforcement Learnin...	2021-06-11	-
5	MuZero	74335.3	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	Ape-X	54681	No	Distributed Prioritized Experience Replay	2018-03-02	Code
7	Agent57	48680.86	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
8	FQF	46498.3	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
9	IMPALA (deep)	43595.78	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
10	R2D2	43223.4	No	-	-	Code
11	IQN	28888	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
12	A3C LSTM hs	23846	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
13	ASL DDQN	21602	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
14	QR-DQN-1	20972	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
15	A3C FF hs	15730.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
16	Prior+Duel noop	15311.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
17	Rainbow	12629	No	Rainbow: Combining Improvements in Deep Reinforc...	2017-10-06	Code
18	Prior+Duel hs	8978	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
19	Duel noop	6427.3	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
20	Duel hs	5993.1	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
21	NoisyNet-Dueling	5909	No	Noisy Networks for Exploration	2017-06-30	Code
22	C51 noop	5747	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
23	Prior hs	3912.1	No	Prioritized Experience Replay	2015-11-18	Code
24	MuZero (Res2 Adam)	3645.63	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
25	Advantage Learning	3460.79	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
26	Persistent AL	3277.59	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
27	A2C + SIL	2951.7	No	Self-Imitation Learning	2018-06-14	Code
28	Bootstrapped DQN	2893	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
29	Prior noop	2865.8	No	Prioritized Experience Replay	2015-11-18	Code
30	DNA	2731	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
31	UCT	2718	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
32	DDQN (tuned) hs	2628.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	DDQN+Pop-Art noop	2589.7	No	Learning values across many orders of magnitude	2016-02-24	-
34	DDQN (tuned) noop	2525.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
35	DreamerV2	2474	No	Mastering Atari with Discrete World Models	2020-10-05	Code
36	A3C FF (1 day) hs	2214.7	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
37	MFEC	1990	No	Model-Free Episodic Control with State Aggregation	2020-08-21	-
38	Nature DQN	1976	No	-	-	Code
39	DQN noop	1692.3	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
40	Recurrent Rational DQN Average	1395	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
41	DQN hs	1293.8	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
42	POP3D	1216.15	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
43	Gorila	1183.3	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
44	MAC	1173.1	No	Mean Actor Critic	2017-09-01	Code
45	DQN Best	1075	No	Playing Atari with Deep Reinforcement Learning	2013-12-19	Code
46	CGP	1001	No	Evolving simple programs for playing Atari games	2018-06-14	Code
47	IDVQ + DRSC + XNES	830	No	Playing Atari with Six Neurons	2018-06-04	Code
48	ES FF (1 hour) noop	678.5	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
49	DDRL A3C	650	No	Distributed Deep Reinforcement Learning: Learn h...	2018-01-09	Code
50	DARQN soft	650	No	Deep Attention Recurrent Q-Network	2015-12-05	Code
51	Rational DQN Average	650	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
52	SARSA	267.9	No	-	-	-
53	Best Learner	250.1	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
54	SAC	160.8	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code

#1GDI-H3(200M frames)SOTA
154380
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-H3
154380
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-I3SOTA
140460
Score· 2021-06-11
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
#4GDI-I3
140460
Score· 2021-06-11
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
#5MuZeroSOTA
74335.3
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6Ape-XSOTA
54681
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#7Agent57
48680.86
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#8FQF
46498.3
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#9IMPALA (deep)SOTA
43595.78
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#10R2D2
43223.4
Score
No paperCode
#11IQN
28888
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#12A3C LSTM hsSOTA
23846
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#13ASL DDQN
21602
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#14QR-DQN-1
20972
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#15A3C FF hs
15730.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#16Prior+Duel noopSOTA
15311.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#17Rainbow
12629
Score· 2017-10-06
Rainbow: Combining Improvements in Deep Reinforcement Learning Code
#18Prior+Duel hsSOTA
8978
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#19Duel noop
6427.3
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#20Duel hs
5993.1
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#21NoisyNet-Dueling
5909
Score· 2017-06-30
Noisy Networks for Exploration Code
#22C51 noop
5747
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#23Prior hs
3912.1
Score· 2015-11-18
Prioritized Experience Replay Code
#24MuZero (Res2 Adam)
3645.63
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#25Advantage Learning
3460.79
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#26Persistent AL
3277.59
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#27A2C + SIL
2951.7
Score· 2018-06-14
Self-Imitation Learning Code
#28Bootstrapped DQN
2893
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#29Prior noop
2865.8
Score· 2015-11-18
Prioritized Experience Replay Code
#30DNA
2731
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#31UCTSOTA
2718
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#32DDQN (tuned) hs
2628.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33DDQN+Pop-Art noop
2589.7
Score· 2016-02-24
Learning values across many orders of magnitude
#34DDQN (tuned) noop
2525.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#35DreamerV2
2474
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#36A3C FF (1 day) hs
2214.7
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#37MFEC
1990
Score· 2020-08-21
Model-Free Episodic Control with State Aggregation
#38Nature DQN
1976
Score
No paperCode
#39DQN noop
1692.3
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#40Recurrent Rational DQN Average
1395
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#41DQN hs
1293.8
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#42POP3D
1216.15
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#43Gorila
1183.3
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#44MAC
1173.1
Score· 2017-09-01
Mean Actor Critic Code
#45DQN Best
1075
Score· 2013-12-19
Playing Atari with Deep Reinforcement Learning Code
#46CGP
1001
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#47IDVQ + DRSC + XNES
830
Score· 2018-06-04
Playing Atari with Six Neurons Code
#48ES FF (1 hour) noop
678.5
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#49DDRL A3C
650
Score· 2018-01-09
Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes Code
#50DARQN soft
650
Score· 2015-12-05
Deep Attention Recurrent Q-Network Code
#51Rational DQN Average
650
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#52SARSA
267.9
Score
No paper
#53Best Learner
250.1
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#54SAC
160.8
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code