Video Games on Atari 2600 Berzerk

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Go-Explore	197376	No	First return, then explore	2020-04-27	Code
2	MuZero	85932.6	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
3	Agent57	61507.83	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
4	Ape-X	57196.7	No	Distributed Prioritized Experience Replay	2018-03-02	Code
5	R2D2	53318.7	No	-	-	Code
6	DNA	19789	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
7	GDI-H3	14649	No	Generalized Data Distribution Iteration	2022-06-07	-
8	FQF	12422.2	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
9	GDI-I3	7607	No	Generalized Data Distribution Iteration	2022-06-07	-
10	GDI-I3	7607	No	Generalized Data Distribution Iteration	2022-06-07	-
11	Prior+Duel noop	3409	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
12	QR-DQN-1	3117	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
13	MuZero (Res2 Adam)	2705.82	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
14	ASL DDQN	2597.2	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
15	Reactor 500M	2303.1	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
16	Prior+Duel hs	2178.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
17	NoisyNet-Dueling	1896	No	Noisy Networks for Exploration	2017-06-30	Code
18	IMPALA (deep)	1852.7	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
19	C51 noop	1645	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
20	Duel noop	1472.6	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
21	A3C FF (1 day) hs	1433.4	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
22	Persistent AL	1328.25	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
23	Prior noop	1305.6	No	Prioritized Experience Replay	2015-11-18	Code
24	DDQN (tuned) noop	1225.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
25	DDQN+Pop-Art noop	1199.6	No	Learning values across many orders of magnitude	2016-02-24	-
26	CGP	1138	No	Evolving simple programs for playing Atari games	2018-06-14	Code
27	IQN	1053	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
28	DDQN (tuned) hs	1011.1	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
29	Duel hs	910.6	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
30	Prior hs	865.9	No	Prioritized Experience Replay	2015-11-18	Code
31	A3C LSTM hs	862.2	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
32	A3C FF hs	817.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
33	DreamerV2	810	No	Mastering Atari with Discrete World Models	2020-10-05	Code
34	Advantage Learning	747.26	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
35	ES FF (1 hour) noop	686	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
36	Best Baseline	670	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
37	DQN noop	585.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	Best Learner	501.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
39	DQN hs	493.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code

#1Go-ExploreSOTA
197376
Score· 2020-04-27
First return, then explore Code
#2MuZeroSOTA
85932.6
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#3Agent57
61507.83
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#4Ape-XSOTA
57196.7
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#5R2D2
53318.7
Score
No paperCode
#6DNA
19789
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#7GDI-H3
14649
Score· 2022-06-07
Generalized Data Distribution Iteration
#8FQF
12422.2
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#9GDI-I3
7607
Score· 2022-06-07
Generalized Data Distribution Iteration
#10GDI-I3
7607
Score· 2022-06-07
Generalized Data Distribution Iteration
#11Prior+Duel noopSOTA
3409
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#12QR-DQN-1
3117
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#13MuZero (Res2 Adam)
2705.82
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#14ASL DDQN
2597.2
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#15Reactor 500M
2303.1
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#16Prior+Duel hsSOTA
2178.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#17NoisyNet-Dueling
1896
Score· 2017-06-30
Noisy Networks for Exploration Code
#18IMPALA (deep)
1852.7
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#19C51 noop
1645
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#20Duel noop
1472.6
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#21A3C FF (1 day) hs
1433.4
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#22Persistent AL
1328.25
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#23Prior noop
1305.6
Score· 2015-11-18
Prioritized Experience Replay Code
#24DDQN (tuned) noop
1225.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#25DDQN+Pop-Art noop
1199.6
Score· 2016-02-24
Learning values across many orders of magnitude
#26CGP
1138
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#27IQN
1053
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#28DDQN (tuned) hs
1011.1
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#29Duel hs
910.6
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#30Prior hs
865.9
Score· 2015-11-18
Prioritized Experience Replay Code
#31A3C LSTM hs
862.2
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#32A3C FF hs
817.9
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#33DreamerV2
810
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#34Advantage Learning
747.26
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#35ES FF (1 hour) noop
686
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#36Best BaselineSOTA
670
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#37DQN noop
585.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38Best Learner
501.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#39DQN hs
493.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code