Atari Games on Atari 2600 Bowling

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	MuZero	260.13	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
2	Go-Explore	260	No	First return, then explore	2020-04-27	Code
3	Agent57	251.18	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
4	R2D2	219.5	No	-	-	Code
5	GDI-H3	205.2	No	Generalized Data Distribution Iteration	2022-06-07	-
6	GDI-I3	201.9	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-I3	201.9	No	Generalized Data Distribution Iteration	2022-06-07	-
8	DNA	181	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
9	RUDDER	179	No	RUDDER: Return Decomposition for Delayed Rewards	2018-06-20	Code
10	MuZero (Res2 Adam)	131.65	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
11	FQF	102.3	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
12	DDQN+Pop-Art noop	102.1	No	Learning values across many orders of magnitude	2016-02-24	-
13	IQN	86.5	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	CGP	85.8	No	Evolving simple programs for playing Atari games	2018-06-14	Code
15	C51 noop	81.8	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
16	Reactor 500M	81	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
17	QR-DQN-1	77.2	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
18	Persistent AL	71.59	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
19	DDQN (tuned) hs	69.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
20	DDQN (tuned) noop	68.1	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
21	Duel hs	65.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
22	Duel noop	65.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
23	ASL DDQN	62.4	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
24	Bootstrapped DQN	60.2	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
25	IMPALA (deep)	59.92	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
26	Advantage Learning	57.41	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
27	DQN hs	56.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
28	Gorila	54	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
29	Prior hs	52	No	Prioritized Experience Replay	2015-11-18	Code
30	DQN noop	50.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
31	Prior+Duel hs	50.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	DreamerV2	49	No	Mastering Atari with Discrete World Models	2020-10-05	Code
33	Prior noop	47.9	No	Prioritized Experience Replay	2015-11-18	Code
34	Prior+Duel noop	46.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
35	Best Learner	43.9	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
36	Nature DQN	42.4	No	-	-	Code
37	A3C LSTM hs	41.8	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
38	POP3D	38.99	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
39	SARSA	36.4	No	-	-	-
40	A3C FF (1 day) hs	36.2	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
41	A3C FF hs	35.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
42	A2C + SIL	31.1	No	Self-Imitation Learning	2018-06-14	Code
43	ES FF (1 hour) noop	30	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
44	Ape-X	17.6	No	Distributed Prioritized Experience Replay	2018-03-02	Code

#1MuZeroSOTA
260.13
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#2Go-Explore
260
Score· 2020-04-27
First return, then explore Code
#3Agent57
251.18
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#4R2D2
219.5
Score
No paperCode
#5GDI-H3
205.2
Score· 2022-06-07
Generalized Data Distribution Iteration
#6GDI-I3
201.9
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-I3
201.9
Score· 2022-06-07
Generalized Data Distribution Iteration
#8DNA
181
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#9RUDDERSOTA
179
Score· 2018-06-20
RUDDER: Return Decomposition for Delayed Rewards Code
#10MuZero (Res2 Adam)
131.65
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#11FQF
102.3
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#12DDQN+Pop-Art noopSOTA
102.1
Score· 2016-02-24
Learning values across many orders of magnitude
#13IQN
86.5
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#14CGP
85.8
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#15C51 noop
81.8
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#16Reactor 500M
81
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#17QR-DQN-1
77.2
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#18Persistent ALSOTA
71.59
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#19DDQN (tuned) hsSOTA
69.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#20DDQN (tuned) noop
68.1
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#21Duel hs
65.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#22Duel noop
65.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#23ASL DDQN
62.4
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#24Bootstrapped DQN
60.2
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#25IMPALA (deep)
59.92
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#26Advantage Learning
57.41
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#27DQN hs
56.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#28GorilaSOTA
54
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#29Prior hs
52
Score· 2015-11-18
Prioritized Experience Replay Code
#30DQN noop
50.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#31Prior+Duel hs
50.4
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32DreamerV2
49
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#33Prior noop
47.9
Score· 2015-11-18
Prioritized Experience Replay Code
#34Prior+Duel noop
46.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#35Best LearnerSOTA
43.9
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#36Nature DQN
42.4
Score
No paperCode
#37A3C LSTM hs
41.8
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#38POP3D
38.99
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#39SARSA
36.4
Score
No paper
#40A3C FF (1 day) hs
36.2
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#41A3C FF hs
35.1
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#42A2C + SIL
31.1
Score· 2018-06-14
Self-Imitation Learning Code
#43ES FF (1 hour) noop
30
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#44Ape-X
17.6
Score· 2018-03-02
Distributed Prioritized Experience Replay Code