Atari Games on Atari 2600 Centipede

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Go-Explore	1422628	No	First return, then explore	2020-04-27	Code
2	GDI-H3(1B frames)	1359533	No	-	-	-
3	MuZero	1159049.27	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
4	MuZero (Res2 Adam)	874301.64	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
5	R2D2	599140.3	No	-	-	Code
6	Agent57	412847.86	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
7	GDI-H3	195630	No	Generalized Data Distribution Iteration	2022-06-07	-
8	GDI-I3	155830	No	Generalized Data Distribution Iteration	2022-06-07	-
9	GDI-I3	155830	No	Generalized Data Distribution Iteration	2022-06-07	-
10	Full Tree	125123	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
11	DNA	100194	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
12	DDQN+Pop-Art noop	49065.8	No	Learning values across many orders of magnitude	2016-02-24	-
13	CGP	24708	No	Evolving simple programs for playing Atari games	2018-06-14	Code
14	Ape-X	12974	No	Distributed Prioritized Experience Replay	2018-03-02	Code
15	QR-DQN-1	12447	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
16	DreamerV2	11883	No	Mastering Atari with Discrete World Models	2020-10-05	Code
17	IQN	11561	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
18	IMPALA (deep)	11049.75	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
19	C51 noop	9646	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
20	Best Learner	8803.8	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
21	Nature DQN	8309	No	-	-	Code
22	ES FF (1 hour) noop	7783.9	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
23	Prior+Duel noop	7687.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
24	NoisyNet-Dueling	7596	No	Noisy Networks for Exploration	2017-06-30	Code
25	Duel noop	7561.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
26	A2C + SIL	7559.5	No	Self-Imitation Learning	2018-06-14	Code
27	Gorila	6296.9	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
28	Prior+Duel hs	5570.2	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
29	DDQN (tuned) noop	5409.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
30	Duel hs	4881	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
31	DQN noop	4657.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	SARSA	4647	No	-	-	-
33	Bootstrapped DQN	4553.5	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
34	Persistent AL	4539.55	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
35	Prior noop	4463.2	No	Prioritized Experience Replay	2015-11-18	Code
36	Advantage Learning	4225.18	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
37	DQN hs	3973.9	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	ASL DDQN	3899.8	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
39	DDQN (tuned) hs	3853.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
40	A3C FF hs	3755.8	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
41	Prior hs	3489.1	No	Prioritized Experience Replay	2015-11-18	Code
42	Reactor 500M	3422	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
43	POP3D	3315.44	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
44	A3C FF (1 day) hs	3306.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
45	A3C LSTM hs	1997	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code

#1Go-ExploreSOTA
1422628
Score· 2020-04-27
First return, then explore Code
#2GDI-H3(1B frames)
1359533
Score
No paper
#3MuZeroSOTA
1159049.27
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#4MuZero (Res2 Adam)
874301.64
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#5R2D2
599140.3
Score
No paperCode
#6Agent57
412847.86
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#7GDI-H3
195630
Score· 2022-06-07
Generalized Data Distribution Iteration
#8GDI-I3
155830
Score· 2022-06-07
Generalized Data Distribution Iteration
#9GDI-I3
155830
Score· 2022-06-07
Generalized Data Distribution Iteration
#10Full TreeSOTA
125123
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#11DNA
100194
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#12DDQN+Pop-Art noop
49065.8
Score· 2016-02-24
Learning values across many orders of magnitude
#13CGP
24708
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#14Ape-X
12974
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#15QR-DQN-1
12447
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#16DreamerV2
11883
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#17IQN
11561
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#18IMPALA (deep)
11049.75
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#19C51 noop
9646
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#20Best Learner
8803.8
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#21Nature DQN
8309
Score
No paperCode
#22ES FF (1 hour) noop
7783.9
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#23Prior+Duel noop
7687.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#24NoisyNet-Dueling
7596
Score· 2017-06-30
Noisy Networks for Exploration Code
#25Duel noop
7561.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#26A2C + SIL
7559.5
Score· 2018-06-14
Self-Imitation Learning Code
#27Gorila
6296.9
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#28Prior+Duel hs
5570.2
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#29DDQN (tuned) noop
5409.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#30Duel hs
4881
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#31DQN noop
4657.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32SARSA
4647
Score
No paper
#33Bootstrapped DQN
4553.5
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#34Persistent AL
4539.55
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#35Prior noop
4463.2
Score· 2015-11-18
Prioritized Experience Replay Code
#36Advantage Learning
4225.18
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#37DQN hs
3973.9
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38ASL DDQN
3899.8
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#39DDQN (tuned) hs
3853.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#40A3C FF hs
3755.8
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#41Prior hs
3489.1
Score· 2015-11-18
Prioritized Experience Replay Code
#42Reactor 500M
3422
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#43POP3D
3315.44
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#44A3C FF (1 day) hs
3306.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#45A3C LSTM hs
1997
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code