Atari Games on Atari 2600 Kung-Fu Master

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	1666665	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-H3 (200M)	1666000	No	-	-	-
3	R2D2	233413.3	No	-	-	Code
4	Agent57	206845.82	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	MuZero	204824	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	GDI-I3	140440	No	Generalized Data Distribution Iteration	2022-06-07	-
7	MuZero (Res2 Adam)	116726.96	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
8	FQF	111138.5	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
9	DNA	110962	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
10	Ape-X	97829.5	No	Distributed Prioritized Experience Replay	2018-03-02	Code
11	ASL DDQN	85182	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
12	QR-DQN-1	76642	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
13	IQN	73512	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	DreamerV2	62741	No	Mastering Atari with Discrete World Models	2020-10-05	Code
15	CGP	57400	No	Evolving simple programs for playing Atari games	2018-06-14	Code
16	UCT	48854.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
17	Prior+Duel noop	48375	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	C51 noop	48192	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
19	IMPALA (deep)	43375.5	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
20	NoisyNet-Dueling	41672	No	Noisy Networks for Exploration	2017-06-30	Code
21	A3C LSTM hs	40835	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
22	Prior noop	39581	No	Prioritized Experience Replay	2015-11-18	Code
23	Prior+Duel hs	37484	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
24	Bootstrapped DQN	36733.3	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
25	Persistent AL	34650.91	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
26	A2C + SIL	34449.2	No	Self-Imitation Learning	2018-06-14	Code
27	DDQN+Pop-Art noop	34393	No	Learning values across many orders of magnitude	2016-02-24	-
28	Duel noop	34294	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
29	POP3D	33728	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
30	Advantage Learning	32182.99	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
31	Prior hs	31676	No	Prioritized Experience Replay	2015-11-18	Code
32	DDQN (tuned) hs	30207	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	DDQN (tuned) noop	29710	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	SARSA	29151	No	-	-	-
35	A3C FF hs	28819	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
36	DQN noop	26059	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
37	Duel hs	24288	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
38	Nature DQN	23270	No	-	-	Code
39	DQN hs	20882	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
40	Gorila	20620	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
41	Best Learner	19544	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	CURL	14280	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
43	A3C FF (1 day) hs	3046	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code

#1GDI-H3SOTA
1666665
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-H3 (200M)
1666000
Score
No paper
#3R2D2
233413.3
Score
No paperCode
#4Agent57SOTA
206845.82
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#5MuZeroSOTA
204824
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6GDI-I3
140440
Score· 2022-06-07
Generalized Data Distribution Iteration
#7MuZero (Res2 Adam)
116726.96
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#8FQFSOTA
111138.5
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#9DNA
110962
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#10Ape-XSOTA
97829.5
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#11ASL DDQN
85182
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#12QR-DQN-1SOTA
76642
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#13IQN
73512
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#14DreamerV2
62741
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#15CGP
57400
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#16UCTSOTA
48854.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#17Prior+Duel noop
48375
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18C51 noop
48192
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#19IMPALA (deep)
43375.5
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#20NoisyNet-Dueling
41672
Score· 2017-06-30
Noisy Networks for Exploration Code
#21A3C LSTM hs
40835
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#22Prior noop
39581
Score· 2015-11-18
Prioritized Experience Replay Code
#23Prior+Duel hs
37484
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#24Bootstrapped DQN
36733.3
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#25Persistent AL
34650.91
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#26A2C + SIL
34449.2
Score· 2018-06-14
Self-Imitation Learning Code
#27DDQN+Pop-Art noop
34393
Score· 2016-02-24
Learning values across many orders of magnitude
#28Duel noop
34294
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#29POP3D
33728
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#30Advantage Learning
32182.99
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#31Prior hs
31676
Score· 2015-11-18
Prioritized Experience Replay Code
#32DDQN (tuned) hs
30207
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33DDQN (tuned) noop
29710
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34SARSA
29151
Score
No paper
#35A3C FF hs
28819
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#36DQN noop
26059
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#37Duel hs
24288
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#38Nature DQN
23270
Score
No paperCode
#39DQN hs
20882
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#40Gorila
20620
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#41Best Learner
19544
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#42CURL
14280
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#43A3C FF (1 day) hs
3046
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code