Video Games on Atari 2600 HERO

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Agent57	114736.26	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
2	MuZero	49244.11	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
3	R2D2	39537.1	No	-	-	Code
4	C51 noop	38874	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
5	GDI-I3	38330	No	Generalized Data Distribution Iteration	2022-06-07	-
6	GDI-I3	38330	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-H3	38225	No	Generalized Data Distribution Iteration	2022-06-07	-
8	MuZero (Res2 Adam)	37234.31	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
9	IMPALA (deep)	33730.55	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
10	A2C + SIL	33156.7	No	Self-Imitation Learning	2018-06-14	Code
11	A3C FF hs	32464.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
12	Ape-X	31655.9	No	Distributed Prioritized Experience Replay	2018-03-02	Code
13	NoisyNet-Dueling	31533	No	Noisy Networks for Exploration	2017-06-30	Code
14	FQF	30926.2	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
15	A3C LSTM hs	28889.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
16	A3C FF (1 day) hs	28765.8	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
17	IQN	28386	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
18	ASL DDQN	26578.5	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
19	DNA	24904	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
20	Advantage Learning	24788.86	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
21	Persistent AL	24175.79	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
22	Prior noop	23037.7	No	Prioritized Experience Replay	2015-11-18	Code
23	DreamerV2	21868	No	Mastering Atari with Discrete World Models	2020-10-05	Code
24	QR-DQN-1	21395	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
25	Prior+Duel noop	21036.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
26	Bootstrapped DQN	21021.3	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
27	Prior hs	20889.9	No	Prioritized Experience Replay	2015-11-18	Code
28	Duel noop	20818.2	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
29	DQN noop	20437.8	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
30	DDQN (tuned) noop	20130.2	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
31	Nature DQN	19950	No	-	-	Code
32	Prior+Duel hs	15459.2	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	Duel hs	15207.9	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	DQN hs	14992.9	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	DDQN (tuned) hs	14892.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
36	DDQN+Pop-Art noop	14225.2	No	Learning values across many orders of magnitude	2016-02-24	-
37	UCT	12859.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
38	MFEC	11732	No	Model-Free Episodic Control with State Aggregation	2020-08-21	-
39	Gorila	8963.4	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
40	SARSA	7295	No	-	-	-
41	Best linear	6459	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	Best Learner	6458.8	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
43	CURL	6235.1	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
44	CGP	2974	No	Evolving simple programs for playing Atari games	2018-06-14	Code

#1Agent57SOTA
114736.26
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#2MuZeroSOTA
49244.11
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#3R2D2
39537.1
Score
No paperCode
#4C51 noopSOTA
38874
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#5GDI-I3
38330
Score· 2022-06-07
Generalized Data Distribution Iteration
#6GDI-I3
38330
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-H3
38225
Score· 2022-06-07
Generalized Data Distribution Iteration
#8MuZero (Res2 Adam)
37234.31
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#9IMPALA (deep)
33730.55
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#10A2C + SIL
33156.7
Score· 2018-06-14
Self-Imitation Learning Code
#11A3C FF hsSOTA
32464.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#12Ape-X
31655.9
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#13NoisyNet-Dueling
31533
Score· 2017-06-30
Noisy Networks for Exploration Code
#14FQF
30926.2
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#15A3C LSTM hs
28889.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#16A3C FF (1 day) hs
28765.8
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#17IQN
28386
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#18ASL DDQN
26578.5
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#19DNA
24904
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#20Advantage LearningSOTA
24788.86
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#21Persistent AL
24175.79
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#22Prior noopSOTA
23037.7
Score· 2015-11-18
Prioritized Experience Replay Code
#23DreamerV2
21868
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#24QR-DQN-1
21395
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#25Prior+Duel noop
21036.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#26Bootstrapped DQN
21021.3
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#27Prior hs
20889.9
Score· 2015-11-18
Prioritized Experience Replay Code
#28Duel noop
20818.2
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#29DQN noopSOTA
20437.8
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#30DDQN (tuned) noop
20130.2
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#31Nature DQN
19950
Score
No paperCode
#32Prior+Duel hs
15459.2
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33Duel hs
15207.9
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34DQN hs
14992.9
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35DDQN (tuned) hs
14892.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#36DDQN+Pop-Art noop
14225.2
Score· 2016-02-24
Learning values across many orders of magnitude
#37UCTSOTA
12859.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#38MFEC
11732
Score· 2020-08-21
Model-Free Episodic Control with State Aggregation
#39Gorila
8963.4
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#40SARSA
7295
Score
No paper
#41Best linear
6459
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#42Best Learner
6458.8
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#43CURL
6235.1
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#44CGP
2974
Score· 2018-06-14
Evolving simple programs for playing Atari games Code