Atari Games on Atari 2600 Amidar

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Agent57	29660.08	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
2	R2D2	29321.4	No	-	-	Code
3	MuZero	28634.39	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
4	Ape-X	8659.2	No	Distributed Prioritized Experience Replay	2018-03-02	Code
5	NoisyNet-Dueling	3537	No	Noisy Networks for Exploration	2017-06-30	Code
6	FQF	3165.3	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
7	IQN	2946	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
8	DreamerV2	2577	No	Mastering Atari with Discrete World Models	2020-10-05	Code
9	Duel noop	2354.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
10	Prior+Duel noop	2296.8	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
11	ASL DDQN	2232.3	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
12	Prior noop	1838.9	No	Prioritized Experience Replay	2015-11-18	Code
13	DDQN (tuned) noop	1793.3	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
14	C51 noop	1735	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
15	QR-DQN-1	1641	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
16	Advantage Learning	1557.43	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
17	IMPALA (deep)	1554.79	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
18	Persistent AL	1451.65	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
19	GDI-I3	1442	No	Generalized Data Distribution Iteration	2022-06-07	-
20	A2C + SIL	1362	No	Self-Imitation Learning	2018-06-14	Code
21	Bootstrapped DQN	1272.5	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
22	MuZero (Res2 Adam)	1197.38	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
23	GDI-H3	1065	No	Generalized Data Distribution Iteration	2022-06-07	-
24	DNA	1025	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
25	Reactor 500M	1015.8	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
26	DQN noop	978	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
27	DDQN+Pop-Art noop	782.5	No	Learning values across many orders of magnitude	2016-02-24	-
28	Nature DQN	739.5	No	-	-	Code
29	POP3D	729.15	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
30	VPN	641	No	Value Prediction Network	2017-07-11	Code
31	A3C FF (1 day) hs	283.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
32	A3C FF hs	263.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
33	Rainbow+SEER	250.5	No	Improving Computational Efficiency in Visual Rei...	2021-03-04	Code
34	Prior+Duel hs	238.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
35	Prior+Duel hs	238.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
36	CURL	232.3	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
37	CGP	199	No	Evolving simple programs for playing Atari games	2018-06-14	Code
38	Gorila	189.2	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
39	SARSA	183.6	No	-	-	-
40	UCT	180.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
41	DQN hs	178.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
42	A3C LSTM hs	173	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
43	Duel hs	172.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
44	DDQN (tuned) hs	169.1	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
45	Prior hs	129.1	No	Prioritized Experience Replay	2015-11-18	Code
46	ES FF (1 hour) noop	112	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
47	Best Learner	103.4	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
48	SAC	7.9	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code

#1Agent57SOTA
29660.08
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#2R2D2
29321.4
Score
No paperCode
#3MuZeroSOTA
28634.39
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#4Ape-XSOTA
8659.2
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#5NoisyNet-DuelingSOTA
3537
Score· 2017-06-30
Noisy Networks for Exploration Code
#6FQF
3165.3
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#7IQN
2946
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#8DreamerV2
2577
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#9Duel noopSOTA
2354.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#10Prior+Duel noop
2296.8
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#11ASL DDQN
2232.3
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#12Prior noopSOTA
1838.9
Score· 2015-11-18
Prioritized Experience Replay Code
#13DDQN (tuned) noop
1793.3
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#14C51 noop
1735
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#15QR-DQN-1
1641
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#16Advantage Learning
1557.43
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#17IMPALA (deep)
1554.79
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#18Persistent AL
1451.65
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#19GDI-I3
1442
Score· 2022-06-07
Generalized Data Distribution Iteration
#20A2C + SIL
1362
Score· 2018-06-14
Self-Imitation Learning Code
#21Bootstrapped DQN
1272.5
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#22MuZero (Res2 Adam)
1197.38
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#23GDI-H3
1065
Score· 2022-06-07
Generalized Data Distribution Iteration
#24DNA
1025
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#25Reactor 500M
1015.8
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#26DQN noopSOTA
978
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#27DDQN+Pop-Art noop
782.5
Score· 2016-02-24
Learning values across many orders of magnitude
#28Nature DQN
739.5
Score
No paperCode
#29POP3D
729.15
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#30VPN
641
Score· 2017-07-11
Value Prediction Network Code
#31A3C FF (1 day) hs
283.9
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#32A3C FF hs
263.9
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#33Rainbow+SEER
250.5
Score· 2021-03-04
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings Code
#34Prior+Duel hs
238.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#35Prior+Duel hs
238.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#36CURL
232.3
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#37CGP
199
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#38GorilaSOTA
189.2
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#39SARSA
183.6
Score
No paper
#40UCTSOTA
180.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#41DQN hs
178.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#42A3C LSTM hs
173
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#43Duel hs
172.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#44DDQN (tuned) hs
169.1
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#45Prior hs
129.1
Score· 2015-11-18
Prioritized Experience Replay Code
#46ES FF (1 hour) noop
112
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#47Best Learner
103.4
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#48SAC
7.9
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code