Video Games on Atari 2600 Defender

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	CGP	993010	No	Evolving simple programs for playing Atari games	2018-06-14	Code
2	GDI-H3	970540	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-I3	893110	No	Generalized Data Distribution Iteration	2022-06-07	-
4	GDI-I3	893110	No	Generalized Data Distribution Iteration	2022-06-07	-
5	MuZero	839642.95	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	Agent57	677642.78	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
7	R2D2	665792	No	-	-	Code
8	MuZero (Res2 Adam)	557200.75	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
9	Ape-X	411943.5	No	Distributed Prioritized Experience Replay	2018-03-02	Code
10	Reactor 500M	223025	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
11	IMPALA (deep)	185203	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
12	DNA	152768	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
13	IQN	53537	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	QR-DQN-1	47887	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
15	NoisyNet-Dueling	42253	No	Noisy Networks for Exploration	2017-06-30	Code
16	Duel noop	42214	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
17	Prior+Duel noop	41324.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	ASL DDQN	37026.5	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
19	Prior+Duel hs	34415	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
20	Persistent AL	32038.93	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
21	Advantage Learning	30643.59	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code

#1CGPSOTA
993010
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#2GDI-H3
970540
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-I3
893110
Score· 2022-06-07
Generalized Data Distribution Iteration
#4GDI-I3
893110
Score· 2022-06-07
Generalized Data Distribution Iteration
#5MuZero
839642.95
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6Agent57
677642.78
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#7R2D2
665792
Score
No paperCode
#8MuZero (Res2 Adam)
557200.75
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#9Ape-XSOTA
411943.5
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#10Reactor 500MSOTA
223025
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#11IMPALA (deep)
185203
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#12DNA
152768
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#13IQN
53537
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#14QR-DQN-1
47887
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#15NoisyNet-Dueling
42253
Score· 2017-06-30
Noisy Networks for Exploration Code
#16Duel noopSOTA
42214
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#17Prior+Duel noop
41324.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18ASL DDQN
37026.5
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#19Prior+Duel hs
34415
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#20Persistent AL
32038.93
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#21Advantage Learning
30643.59
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code