Atari Games on Atari 2600 Alien

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	MuZero	741812.63	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
2	Agent57	297638.17	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
3	GDI-H3(1B frames)	279700	No	-	-	-
4	R2D2	229496.9	No	-	-	Code
5	MuZero (Res2 Adam)	70192.35	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
6	GDI-H3	48735	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-I3	43384	No	Generalized Data Distribution Iteration	2022-06-07	-
8	Ape-X	40804.9	No	Distributed Prioritized Experience Replay	2018-03-02	Code
9	FQF	16754.6	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
10	IMPALA (deep)	15962.1	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
11	Reactor 500M	12689.1	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
12	UCT	7785	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
13	IQN	7022	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	ASL DDQN	6955.2	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
15	NoisyNet-Dueling	5778	No	Noisy Networks for Exploration	2017-06-30	Code
16	Persistent AL	5699.81	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
17	DNA	5021	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
18	Advantage Learning	4990.91	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
19	QR-DQN-1	4871	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
20	Duel noop	4461.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
21	Prior noop	4203.8	No	Prioritized Experience Replay	2015-11-18	Code
22	DreamerV2	3967	No	Mastering Atari with Discrete World Models	2020-10-05	Code
23	Prior+Duel noop	3941	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
24	DDQN (tuned) noop	3747.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
25	DDQN+Pop-Art noop	3213.5	No	Learning values across many orders of magnitude	2016-02-24	-
26	C51 noop	3166	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
27	Nature DQN	3069	No	-	-	Code
28	Bootstrapped DQN	2436.6	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
29	A2C + SIL	2242.2	No	Self-Imitation Learning	2018-06-14	Code
30	CGP	1978	No	Evolving simple programs for playing Atari games	2018-06-14	Code
31	DQN noop	1620	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	POP3D	1510.8	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
33	Duel hs	1486.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	VPN	1429	No	Value Prediction Network	2017-07-11	Code
35	Prior hs	1334.7	No	Prioritized Experience Replay	2015-11-18	Code
36	Rainbow+SEER	1172.6	No	Improving Computational Efficiency in Visual Rei...	2021-03-04	Code
37	CURL	1148.2	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
38	DDQN (tuned) hs	1033.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
39	ES FF (1 hour) noop	994	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
40	A3C LSTM hs	945.3	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
41	Best Learner	939.2	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	Prior+Duel hs	823.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
43	Prior+Duel hs	823.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
44	Gorila	813.5	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
45	DQN hs	634	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
46	A3C FF hs	518.4	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
47	SAC	216.9	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code
48	A3C FF (1 day) hs	182.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
49	SARSA	103.2	No	-	-	-

#1MuZeroSOTA
741812.63
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#2Agent57
297638.17
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#3GDI-H3(1B frames)
279700
Score
No paper
#4R2D2
229496.9
Score
No paperCode
#5MuZero (Res2 Adam)
70192.35
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#6GDI-H3
48735
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-I3
43384
Score· 2022-06-07
Generalized Data Distribution Iteration
#8Ape-XSOTA
40804.9
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#9FQF
16754.6
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#10IMPALA (deep)SOTA
15962.1
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#11Reactor 500MSOTA
12689.1
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#12UCTSOTA
7785
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#13IQN
7022
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#14ASL DDQN
6955.2
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#15NoisyNet-Dueling
5778
Score· 2017-06-30
Noisy Networks for Exploration Code
#16Persistent AL
5699.81
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#17DNA
5021
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#18Advantage Learning
4990.91
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#19QR-DQN-1
4871
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#20Duel noop
4461.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#21Prior noop
4203.8
Score· 2015-11-18
Prioritized Experience Replay Code
#22DreamerV2
3967
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#23Prior+Duel noop
3941
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#24DDQN (tuned) noop
3747.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#25DDQN+Pop-Art noop
3213.5
Score· 2016-02-24
Learning values across many orders of magnitude
#26C51 noop
3166
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#27Nature DQN
3069
Score
No paperCode
#28Bootstrapped DQN
2436.6
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#29A2C + SIL
2242.2
Score· 2018-06-14
Self-Imitation Learning Code
#30CGP
1978
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#31DQN noop
1620
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32POP3D
1510.8
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#33Duel hs
1486.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34VPN
1429
Score· 2017-07-11
Value Prediction Network Code
#35Prior hs
1334.7
Score· 2015-11-18
Prioritized Experience Replay Code
#36Rainbow+SEER
1172.6
Score· 2021-03-04
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings Code
#37CURL
1148.2
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#38DDQN (tuned) hs
1033.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#39ES FF (1 hour) noop
994
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#40A3C LSTM hs
945.3
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#41Best Learner
939.2
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#42Prior+Duel hs
823.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#43Prior+Duel hs
823.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#44Gorila
813.5
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#45DQN hs
634
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#46A3C FF hs
518.4
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#47SAC
216.9
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code
#48A3C FF (1 day) hs
182.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#49SARSA
103.2
Score
No paper