Atari Games on Atari 2600 Asterix

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	999999	No	Generalized Data Distribution Iteration	2022-06-07	-
2	R2D2	999153.3	No	-	-	Code
3	MuZero	998425	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
4	Agent57	991384.42	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	MuZero (Res2 Adam)	862406.65	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
6	GDI-I3	759910	No	Generalized Data Distribution Iteration	2022-06-07	-
7	FQF	578388.5	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
8	ASL DDQN	567640	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
9	C51 noop	406211	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
10	Prior+Duel noop	375080	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
11	Prior+Duel hs	364200	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
12	Prior+Duel hs	364200	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
13	IQN	342016	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	DNA	323965	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
15	Ape-X	313305	No	Distributed Prioritized Experience Replay	2018-03-02	Code
16	IMPALA (deep)	300732	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
17	UCT	290700	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
18	QR-DQN-1	261025	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
19	Reactor 500M	205914	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
20	DreamerV2	72311	No	Mastering Atari with Discrete World Models	2020-10-05	Code
21	Prior noop	31527	No	Prioritized Experience Replay	2015-11-18	Code
22	NoisyNet-Dueling	28350	No	Noisy Networks for Exploration	2017-06-30	Code
23	Duel noop	28188	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
24	Prior hs	22484.5	No	Prioritized Experience Replay	2015-11-18	Code
25	A3C FF hs	22140.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
26	RIMs-PPO	21040	No	-	-	-
27	Bootstrapped DQN	19713.2	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
28	Persistent AL	19564.9	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
29	DDQN+Pop-Art noop	18919.5	No	Learning values across many orders of magnitude	2016-02-24	-
30	Rational DQN Average	18109	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
31	A2C + SIL	17984.2	No	Self-Imitation Learning	2018-06-14	Code
32	DDQN (tuned) noop	17356.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
33	A3C LSTM hs	17244.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
34	DDQN (tuned) hs	16837	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	Duel hs	15840	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
36	Advantage Learning	12852.08	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
37	Recurrent Rational DQN Average	12621	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
38	A3C FF (1 day) hs	6723	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
39	Nature DQN	6012	No	-	-	Code
40	DQN noop	4359	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
41	POP3D	4310.67	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
42	Gorila	3324.7	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
43	DQN hs	3170.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
44	CGP	1880	No	Evolving simple programs for playing Atari games	2018-06-14	Code
45	ES FF (1 hour) noop	1440	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
46	SARSA	1332	No	-	-	-
47	Best Learner	987.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
48	CURL	524.3	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
49	SAC	272	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code

#1GDI-H3SOTA
999999
Score· 2022-06-07
Generalized Data Distribution Iteration
#2R2D2
999153.3
Score
No paperCode
#3MuZeroSOTA
998425
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#4Agent57
991384.42
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#5MuZero (Res2 Adam)
862406.65
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#6GDI-I3
759910
Score· 2022-06-07
Generalized Data Distribution Iteration
#7FQFSOTA
578388.5
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#8ASL DDQN
567640
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#9C51 noopSOTA
406211
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#10Prior+Duel noopSOTA
375080
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#11Prior+Duel hs
364200
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#12Prior+Duel hs
364200
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#13IQN
342016
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#14DNA
323965
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#15Ape-X
313305
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#16IMPALA (deep)
300732
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#17UCTSOTA
290700
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#18QR-DQN-1
261025
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#19Reactor 500M
205914
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#20DreamerV2
72311
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#21Prior noop
31527
Score· 2015-11-18
Prioritized Experience Replay Code
#22NoisyNet-Dueling
28350
Score· 2017-06-30
Noisy Networks for Exploration Code
#23Duel noop
28188
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#24Prior hs
22484.5
Score· 2015-11-18
Prioritized Experience Replay Code
#25A3C FF hs
22140.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#26RIMs-PPO
21040
Score
No paper
#27Bootstrapped DQN
19713.2
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#28Persistent AL
19564.9
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#29DDQN+Pop-Art noop
18919.5
Score· 2016-02-24
Learning values across many orders of magnitude
#30Rational DQN Average
18109
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#31A2C + SIL
17984.2
Score· 2018-06-14
Self-Imitation Learning Code
#32DDQN (tuned) noop
17356.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#33A3C LSTM hs
17244.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#34DDQN (tuned) hs
16837
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35Duel hs
15840
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#36Advantage Learning
12852.08
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#37Recurrent Rational DQN Average
12621
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#38A3C FF (1 day) hs
6723
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#39Nature DQN
6012
Score
No paperCode
#40DQN noop
4359
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#41POP3D
4310.67
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#42Gorila
3324.7
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#43DQN hs
3170.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#44CGP
1880
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#45ES FF (1 hour) noop
1440
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#46SARSA
1332
Score
No paper
#47Best Learner
987.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#48CURL
524.3
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#49SAC
272
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code