Atari Games on Atari 2600 Double Dunk

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	UCT	24	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
2	GDI-H3	24	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-I3	24	No	Generalized Data Distribution Iteration	2022-06-07	-
4	GDI-H3	24	No	Generalized Data Distribution Iteration	2022-06-07	-
5	MuZero	23.94	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	Agent57	23.93	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
7	MuZero (Res2 Adam)	23.91	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
8	R2D2	23.7	No	-	-	Code
9	Ape-X	23.5	No	Distributed Prioritized Experience Replay	2018-03-02	Code
10	Reactor 500M	23	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
11	QR-DQN-1	21.9	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
12	A2C + SIL	21.5	No	Self-Imitation Learning	2018-06-14	Code
13	Prior noop	18.5	No	Prioritized Experience Replay	2015-11-18	Code
14	DreamerV2	17	No	Mastering Atari with Discrete World Models	2020-10-05	Code
15	Prior hs	16	No	Prioritized Experience Replay	2015-11-18	Code
16	IQN	5.6	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
17	Bootstrapped DQN	3	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
18	C51 noop	2.5	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
19	CGP	2	No	Evolving simple programs for playing Atari games	2018-06-14	Code
20	NoisyNet-Dueling	1	No	Noisy Networks for Exploration	2017-06-30	Code
21	ES FF (1 hour) noop	0.2	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
22	Duel noop	0.1	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
23	A3C FF (1 day) hs	0.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
24	A3C LSTM hs	0.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
25	ASL DDQN	0.1	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
26	A3C FF hs	-0.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
27	Advantage Learning	-0.15	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
28	DDQN (tuned) hs	-0.3	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
29	IMPALA (deep)	-0.33	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
30	Duel hs	-0.8	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
31	DNA	-1.3	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
32	Persistent AL	-2.51	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
33	DDQN (tuned) noop	-5.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	DQN hs	-6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	DQN noop	-6.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
36	POP3D	-7.89	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
37	Prior+Duel hs	-10.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	Gorila	-11.3	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
39	DDQN+Pop-Art noop	-11.5	No	Learning values across many orders of magnitude	2016-02-24	-
40	Prior+Duel noop	-12.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
41	Best Learner	-13.1	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	SARSA	-16	No	-	-	-
43	Nature DQN	-18.1	No	-	-	Code

#1UCTSOTA
24
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#2GDI-H3
24
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-I3
24
Score· 2022-06-07
Generalized Data Distribution Iteration
#4GDI-H3
24
Score· 2022-06-07
Generalized Data Distribution Iteration
#5MuZero
23.94
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6Agent57
23.93
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#7MuZero (Res2 Adam)
23.91
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#8R2D2
23.7
Score
No paperCode
#9Ape-X
23.5
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#10Reactor 500M
23
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#11QR-DQN-1
21.9
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#12A2C + SIL
21.5
Score· 2018-06-14
Self-Imitation Learning Code
#13Prior noop
18.5
Score· 2015-11-18
Prioritized Experience Replay Code
#14DreamerV2
17
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#15Prior hs
16
Score· 2015-11-18
Prioritized Experience Replay Code
#16IQN
5.6
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#17Bootstrapped DQN
3
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#18C51 noop
2.5
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#19CGP
2
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#20NoisyNet-Dueling
1
Score· 2017-06-30
Noisy Networks for Exploration Code
#21ES FF (1 hour) noop
0.2
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#22Duel noop
0.1
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#23A3C FF (1 day) hs
0.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#24A3C LSTM hs
0.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#25ASL DDQN
0.1
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#26A3C FF hs
-0.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#27Advantage Learning
-0.15
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#28DDQN (tuned) hs
-0.3
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#29IMPALA (deep)
-0.33
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#30Duel hs
-0.8
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#31DNA
-1.3
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#32Persistent AL
-2.51
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#33DDQN (tuned) noop
-5.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34DQN hs
-6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35DQN noop
-6.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#36POP3D
-7.89
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#37Prior+Duel hs
-10.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38Gorila
-11.3
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#39DDQN+Pop-Art noop
-11.5
Score· 2016-02-24
Learning values across many orders of magnitude
#40Prior+Duel noop
-12.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#41Best Learner
-13.1
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#42SARSA
-16
Score
No paper
#43Nature DQN
-18.1
Score
No paperCode