Atari Games on Atari 2600 Time Pilot

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	MuZero	476763.9	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
2	GDI-H3	450810	No	Generalized Data Distribution Iteration	2022-06-07	-
3	R2D2	445377.3	No	-	-	Code
4	MuZero (Res2 Adam)	424011.16	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
5	Agent57	405425.31	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
6	GDI-I3	216770	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-I3	216770	No	Generalized Data Distribution Iteration	2022-06-07	-
8	Ape-X	87085	No	Distributed Prioritized Experience Replay	2018-03-02	Code
9	UCT	63854.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
10	IMPALA (deep)	48481.5	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
11	DreamerV2	37945	No	Mastering Atari with Discrete World Models	2020-10-05	Code
12	A3C LSTM hs	27202	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
13	Rational DQN Average	17632	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
14	NoisyNet-Dueling	17301	No	Noisy Networks for Exploration	2017-06-30	Code
15	Recurrent Rational DQN Average	13261	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
16	DNA	12774	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
17	A3C FF hs	12679	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
18	IQN	12236	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
19	ASL DDQN	12071	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
20	CGP	12040	No	Evolving simple programs for playing Atari games	2018-06-14	Code
21	Duel noop	11666	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
22	A2C + SIL	10811.7	No	Self-Imitation Learning	2018-06-14	Code
23	QR-DQN-1	10345	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
24	Prior noop	9197	No	Prioritized Experience Replay	2015-11-18	Code
25	Bootstrapped DQN	9079.4	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
26	Advantage Learning	8969.12	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
27	DDQN (tuned) noop	8339	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
28	C51 noop	8329	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
29	Gorila	8267.8	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
30	Prior+Duel noop	7553	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
31	DDQN (tuned) hs	6608	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	Duel hs	6601	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
33	Prior hs	5963	No	Prioritized Experience Replay	2015-11-18	Code
34	Nature DQN	5947	No	-	-	Code
35	A3C FF (1 day) hs	5825	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
36	ES FF (1 hour) noop	4970	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
37	Prior+Duel hs	4871	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	DQN noop	4870	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
39	DDQN+Pop-Art noop	4870	No	Learning values across many orders of magnitude	2016-02-24	-
40	DQN hs	4786	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
41	IDVQ + DRSC + XNES	4600	No	Playing Atari with Six Neurons	2018-06-04	Code
42	POP3D	3770.33	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
43	Best Learner	3741.2	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
44	SARSA	24.9	No	-	-	-

#1MuZeroSOTA
476763.9
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#2GDI-H3
450810
Score· 2022-06-07
Generalized Data Distribution Iteration
#3R2D2
445377.3
Score
No paperCode
#4MuZero (Res2 Adam)
424011.16
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#5Agent57
405425.31
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#6GDI-I3
216770
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-I3
216770
Score· 2022-06-07
Generalized Data Distribution Iteration
#8Ape-XSOTA
87085
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#9UCTSOTA
63854.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#10IMPALA (deep)
48481.5
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#11DreamerV2
37945
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#12A3C LSTM hs
27202
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#13Rational DQN Average
17632
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#14NoisyNet-Dueling
17301
Score· 2017-06-30
Noisy Networks for Exploration Code
#15Recurrent Rational DQN Average
13261
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#16DNA
12774
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#17A3C FF hs
12679
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#18IQN
12236
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#19ASL DDQN
12071
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#20CGP
12040
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#21Duel noop
11666
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#22A2C + SIL
10811.7
Score· 2018-06-14
Self-Imitation Learning Code
#23QR-DQN-1
10345
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#24Prior noop
9197
Score· 2015-11-18
Prioritized Experience Replay Code
#25Bootstrapped DQN
9079.4
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#26Advantage Learning
8969.12
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#27DDQN (tuned) noop
8339
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#28C51 noop
8329
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#29Gorila
8267.8
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#30Prior+Duel noop
7553
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#31DDQN (tuned) hs
6608
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32Duel hs
6601
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#33Prior hs
5963
Score· 2015-11-18
Prioritized Experience Replay Code
#34Nature DQN
5947
Score
No paperCode
#35A3C FF (1 day) hs
5825
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#36ES FF (1 hour) noop
4970
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#37Prior+Duel hs
4871
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38DQN noop
4870
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#39DDQN+Pop-Art noop
4870
Score· 2016-02-24
Learning values across many orders of magnitude
#40DQN hs
4786
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#41IDVQ + DRSC + XNES
4600
Score· 2018-06-04
Playing Atari with Six Neurons Code
#42POP3D
3770.33
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#43Best Learner
3741.2
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#44SARSA
24.9
Score
No paper