Atari Games on Atari 2600 Demon Attack

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	787985	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-I3	675530	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-I3	675530	No	Generalized Data Distribution Iteration	2022-06-07	-
4	RIMs-PPO	230324	No	-	-	-
5	MuZero	143964.26	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	MuZero (Res2 Adam)	143838.04	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
7	Agent57	143161.44	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
8	R2D2	140002.3	No	-	-	Code
9	Ape-X	133086.4	No	Distributed Prioritized Experience Replay	2018-03-02	Code
10	IMPALA (deep)	132826.98	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
11	C51 noop	130955	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
12	IQN	128580	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
13	QR-DQN-1	121551	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
14	ASL DDQN	119773.9	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
15	A3C LSTM hs	115201.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
16	Reactor 500M	115154	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
17	A3C FF hs	113308.4	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
18	DNA	97909	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
19	A3C FF (1 day) hs	84997.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
20	Bootstrapped DQN	82610	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
21	DreamerV2	82263	No	Mastering Atari with Discrete World Models	2020-10-05	Code
22	Prior+Duel hs	73371.3	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
23	Prior+Duel noop	72878.6	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
24	Prior noop	71846.4	No	Prioritized Experience Replay	2015-11-18	Code
25	Persistent AL	70908.17	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
26	DDQN (tuned) hs	69803.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
27	NoisyNet-Dueling	69311	No	Noisy Networks for Exploration	2017-06-30	Code
28	DDQN+Pop-Art noop	63644.9	No	Learning values across many orders of magnitude	2016-02-24	-
29	Prior hs	61277.5	No	Prioritized Experience Replay	2015-11-18	Code
30	POP3D	61147.33	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
31	Duel noop	60813.3	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
32	DDQN (tuned) noop	58044.2	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
33	Duel hs	56322.8	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	UCT	28158.8	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
35	Advantage Learning	27153.48	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
36	Gorila	14880.1	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
37	DQN hs	12550.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	DQN noop	12149.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
39	A2C + SIL	10140.5	No	Self-Imitation Learning	2018-06-14	Code
40	Nature DQN	9711	No	-	-	Code
41	CGP	2387	No	Evolving simple programs for playing Atari games	2018-06-14	Code
42	ES FF (1 hour) noop	1166.5	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
43	CURL	834	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
44	Best Learner	520.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
45	IDVQ + DRSC + XNES	325	No	Playing Atari with Six Neurons	2018-06-04	Code
46	SARSA	0	No	-	-	-

#1GDI-H3SOTA
787985
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-I3
675530
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-I3
675530
Score· 2022-06-07
Generalized Data Distribution Iteration
#4RIMs-PPO
230324
Score
No paper
#5MuZeroSOTA
143964.26
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6MuZero (Res2 Adam)
143838.04
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#7Agent57
143161.44
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#8R2D2
140002.3
Score
No paperCode
#9Ape-XSOTA
133086.4
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#10IMPALA (deep)SOTA
132826.98
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#11C51 noopSOTA
130955
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#12IQN
128580
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#13QR-DQN-1
121551
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#14ASL DDQN
119773.9
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#15A3C LSTM hsSOTA
115201.9
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#16Reactor 500M
115154
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#17A3C FF hs
113308.4
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#18DNA
97909
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#19A3C FF (1 day) hs
84997.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#20Bootstrapped DQN
82610
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#21DreamerV2
82263
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#22Prior+Duel hsSOTA
73371.3
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#23Prior+Duel noop
72878.6
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#24Prior noop
71846.4
Score· 2015-11-18
Prioritized Experience Replay Code
#25Persistent AL
70908.17
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#26DDQN (tuned) hs
69803.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#27NoisyNet-Dueling
69311
Score· 2017-06-30
Noisy Networks for Exploration Code
#28DDQN+Pop-Art noop
63644.9
Score· 2016-02-24
Learning values across many orders of magnitude
#29Prior hs
61277.5
Score· 2015-11-18
Prioritized Experience Replay Code
#30POP3D
61147.33
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#31Duel noop
60813.3
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#32DDQN (tuned) noop
58044.2
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#33Duel hs
56322.8
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34UCTSOTA
28158.8
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#35Advantage Learning
27153.48
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#36Gorila
14880.1
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#37DQN hs
12550.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38DQN noop
12149.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#39A2C + SIL
10140.5
Score· 2018-06-14
Self-Imitation Learning Code
#40Nature DQN
9711
Score
No paperCode
#41CGP
2387
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#42ES FF (1 hour) noop
1166.5
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#43CURL
834
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#44Best Learner
520.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#45IDVQ + DRSC + XNES
325
Score· 2018-06-04
Playing Atari with Six Neurons Code
#46SARSA
0
Score
No paper