Video Games on Atari 2600 Video Pinball

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	R2D2	999383.2	No	-	-	Code
2	Agent57	992340.74	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
3	MuZero	981791.88	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
4	GDI-H3	978190	No	Generalized Data Distribution Iteration	2022-06-07	-
5	C51 noop	949604	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
6	GDI-I3	925830	No	Generalized Data Distribution Iteration	2022-06-07	-
7	NoisyNet-Dueling	870954	No	Noisy Networks for Exploration	2017-06-30	Code
8	MuZero (Res2 Adam)	865543.44	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
9	Bootstrapped DQN	811610	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
10	QR-DQN-1	705662	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
11	IQN	698045	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
12	ASL DDQN	626794	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
13	IMPALA (deep)	572898.27	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
14	Ape-X	565163.2	No	Distributed Prioritized Experience Replay	2018-03-02	Code
15	Advantage Learning	543504	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
16	DNA	505392	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
17	Prior+Duel noop	479197	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	A3C LSTM hs	470310.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
19	A2C + SIL	461522.4	No	Self-Imitation Learning	2018-06-14	Code
20	Prior+Duel hs	447408.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
21	DDQN (tuned) hs	367823.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
22	A3C FF hs	331628.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
23	DDQN (tuned) noop	309941.9	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
24	Prior hs	295972.8	No	Prioritized Experience Replay	2015-11-18	Code
25	Prior noop	282007.3	No	Prioritized Experience Replay	2015-11-18	Code
26	UCT	254748	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
27	DQN noop	196760.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
28	A3C FF (1 day) hs	185852.6	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
29	DQN hs	154414.1	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
30	Rational DQN Average	149712	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
31	Gorila	112093.4	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
32	Duel hs	110976.2	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
33	Duel noop	98209.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	Recurrent Rational DQN Average	86942	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
35	DDQN+Pop-Art noop	56287	No	Learning values across many orders of magnitude	2016-02-24	-
36	Nature DQN	42684	No	-	-	Code
37	DreamerV2	41860	No	Mastering Atari with Discrete World Models	2020-10-05	Code
38	POP3D	37780.7	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
39	CGP	33752.4	No	Evolving simple programs for playing Atari games	2018-06-14	Code
40	ES FF (1 hour) noop	22834.8	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
41	SARSA	19761	No	-	-	-
42	Best Learner	16871.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code

#1R2D2
999383.2
Score
No paperCode
#2Agent57SOTA
992340.74
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#3MuZeroSOTA
981791.88
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#4GDI-H3
978190
Score· 2022-06-07
Generalized Data Distribution Iteration
#5C51 noopSOTA
949604
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#6GDI-I3
925830
Score· 2022-06-07
Generalized Data Distribution Iteration
#7NoisyNet-DuelingSOTA
870954
Score· 2017-06-30
Noisy Networks for Exploration Code
#8MuZero (Res2 Adam)
865543.44
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#9Bootstrapped DQNSOTA
811610
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#10QR-DQN-1
705662
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#11IQN
698045
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#12ASL DDQN
626794
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#13IMPALA (deep)
572898.27
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#14Ape-X
565163.2
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#15Advantage LearningSOTA
543504
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#16DNA
505392
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#17Prior+Duel noopSOTA
479197
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18A3C LSTM hs
470310.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#19A2C + SIL
461522.4
Score· 2018-06-14
Self-Imitation Learning Code
#20Prior+Duel hsSOTA
447408.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#21DDQN (tuned) hs
367823.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#22A3C FF hs
331628.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#23DDQN (tuned) noop
309941.9
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#24Prior hs
295972.8
Score· 2015-11-18
Prioritized Experience Replay Code
#25Prior noop
282007.3
Score· 2015-11-18
Prioritized Experience Replay Code
#26UCTSOTA
254748
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#27DQN noop
196760.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#28A3C FF (1 day) hs
185852.6
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#29DQN hs
154414.1
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#30Rational DQN Average
149712
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#31Gorila
112093.4
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#32Duel hs
110976.2
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#33Duel noop
98209.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34Recurrent Rational DQN Average
86942
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#35DDQN+Pop-Art noop
56287
Score· 2016-02-24
Learning values across many orders of magnitude
#36Nature DQN
42684
Score
No paperCode
#37DreamerV2
41860
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#38POP3D
37780.7
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#39CGP
33752.4
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#40ES FF (1 hour) noop
22834.8
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#41SARSA
19761
Score
No paper
#42Best Learner
16871.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code