Atari Games on Atari 2600 Enduro

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-I3	14330	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-I3	14330	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-H3	14300	No	Generalized Data Distribution Iteration	2022-06-07	-
4	C51 noop	3454	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
5	MuZero	2382.44	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	R2D2	2372.7	No	-	-	Code
7	Agent57	2367.71	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
8	MuZero (Res2 Adam)	2365.81	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
9	IQN	2359	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
10	QR-DQN-1	2355	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
11	Prior+Duel noop	2306.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
12	Duel noop	2258.2	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
13	Reactor 500M	2224.2	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
14	Prior+Duel hs	2223.9	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
15	Ape-X	2177.4	No	Distributed Prioritized Experience Replay	2018-03-02	Code
16	ASL DDQN	2103.1	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
17	Prior noop	2093	No	Prioritized Experience Replay	2015-11-18	Code
18	Duel hs	2077.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
19	DNA	2059	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
20	NoisyNet-Dueling	2013	No	Noisy Networks for Exploration	2017-06-30	Code
21	DDQN+Pop-Art noop	2002.1	No	Learning values across many orders of magnitude	2016-02-24	-
22	Prior hs	1831	No	Prioritized Experience Replay	2015-11-18	Code
23	DreamerV2	1656	No	Mastering Atari with Discrete World Models	2020-10-05	Code
24	Bootstrapped DQN	1591	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
25	Persistent AL	1343.1	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
26	Advantage Learning	1252.7	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
27	DDQN (tuned) hs	1216.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
28	DDQN (tuned) noop	1211.8	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
29	A2C + SIL	1205.1	No	Self-Imitation Learning	2018-06-14	Code
30	Rational DQN Average	1043	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
31	Recurrent Rational DQN Average	957	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
32	DQN noop	729	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	DQN Best	661	No	Playing Atari with Deep Reinforcement Learning	2013-12-19	Code
34	DQN hs	626.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	POP3D	459.85	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
36	VPN	382	No	Value Prediction Network	2017-07-11	Code
37	Nature DQN	301.8	No	-	-	Code
38	UCT	286.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
39	SARSA	159.4	No	-	-	-
40	Best Learner	129.1	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
41	ES FF (1 hour) noop	95	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
42	Gorila	71	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
43	CGP	56.8	No	Evolving simple programs for playing Atari games	2018-06-14	Code
44	SAC	0.8	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code
45	IMPALA (deep)	0	No	-	-	Code
46	A3C FF (1 day) hs	-82.2	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
47	A3C FF hs	-82.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
48	A3C LSTM hs	-82.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code

#1GDI-I3SOTA
14330
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-I3
14330
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-H3
14300
Score· 2022-06-07
Generalized Data Distribution Iteration
#4C51 noopSOTA
3454
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#5MuZero
2382.44
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6R2D2
2372.7
Score
No paperCode
#7Agent57
2367.71
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#8MuZero (Res2 Adam)
2365.81
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#9IQN
2359
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#10QR-DQN-1
2355
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#11Prior+Duel noopSOTA
2306.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#12Duel noop
2258.2
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#13Reactor 500M
2224.2
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#14Prior+Duel hsSOTA
2223.9
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#15Ape-X
2177.4
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#16ASL DDQN
2103.1
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#17Prior noop
2093
Score· 2015-11-18
Prioritized Experience Replay Code
#18Duel hs
2077.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#19DNA
2059
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#20NoisyNet-Dueling
2013
Score· 2017-06-30
Noisy Networks for Exploration Code
#21DDQN+Pop-Art noop
2002.1
Score· 2016-02-24
Learning values across many orders of magnitude
#22Prior hs
1831
Score· 2015-11-18
Prioritized Experience Replay Code
#23DreamerV2
1656
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#24Bootstrapped DQN
1591
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#25Persistent AL
1343.1
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#26Advantage Learning
1252.7
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#27DDQN (tuned) hs
1216.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#28DDQN (tuned) noop
1211.8
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#29A2C + SIL
1205.1
Score· 2018-06-14
Self-Imitation Learning Code
#30Rational DQN Average
1043
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#31Recurrent Rational DQN Average
957
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#32DQN noop
729
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33DQN BestSOTA
661
Score· 2013-12-19
Playing Atari with Deep Reinforcement Learning Code
#34DQN hs
626.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35POP3D
459.85
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#36VPN
382
Score· 2017-07-11
Value Prediction Network Code
#37Nature DQN
301.8
Score
No paperCode
#38UCTSOTA
286.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#39SARSA
159.4
Score
No paper
#40Best Learner
129.1
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#41ES FF (1 hour) noop
95
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#42Gorila
71
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#43CGP
56.8
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#44SAC
0.8
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code
#45IMPALA (deep)
0
Score
No paperCode
#46A3C FF (1 day) hs
-82.2
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#47A3C FF hs
-82.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#48A3C LSTM hs
-82.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code