Video Games on Atari 2600 Robotank

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	MuZero	131.13	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
2	Agent57	127.32	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
3	GDI-H3	113.4	No	Generalized Data Distribution Iteration	2022-06-07	-
4	GDI-I3	108.2	No	Generalized Data Distribution Iteration	2022-06-07	-
5	GDI-I3	108.2	No	Generalized Data Distribution Iteration	2022-06-07	-
6	MuZero (Res2 Adam)	100.59	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
7	R2D2	100.4	No	-	-	Code
8	DreamerV2	78	No	Mastering Atari with Discrete World Models	2020-10-05	Code
9	FQF	75.7	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
10	Ape-X	73.8	No	Distributed Prioritized Experience Replay	2018-03-02	Code
11	Advantage Learning	69.31	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
12	Bootstrapped DQN	66.6	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
13	ASL DDQN	65.8	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
14	Duel noop	65.3	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
15	DDQN (tuned) noop	65.1	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
16	DNA	64.8	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
17	DDQN+Pop-Art noop	64.3	No	Learning values across many orders of magnitude	2016-02-24	-
18	NoisyNet-Dueling	64	No	Noisy Networks for Exploration	2017-06-30	Code
19	DQN noop	63.9	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
20	Prior noop	62.6	No	Prioritized Experience Replay	2015-11-18	Code
21	IQN	62.5	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
22	Duel hs	62	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
23	Gorila	61.8	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
24	QR-DQN-1	59.4	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
25	DDQN (tuned) hs	59.1	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
26	DQN hs	58.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
27	Prior hs	56.2	No	Prioritized Experience Replay	2015-11-18	Code
28	C51 noop	52.3	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
29	Nature DQN	51.6	No	-	-	Code
30	UCT	50.4	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
31	A3C FF hs	32.8	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
32	Best Learner	28.7	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
33	Prior+Duel noop	27.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
34	Prior+Duel hs	24.7	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	CGP	24.2	No	Evolving simple programs for playing Atari games	2018-06-14	Code
36	IMPALA (deep)	12.96	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
37	SARSA	12.4	No	-	-	-
38	ES FF (1 hour) noop	11.9	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
39	A2C + SIL	10.5	No	Self-Imitation Learning	2018-06-14	Code
40	POP3D	4.6	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
41	A3C LSTM hs	2.6	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
42	A3C FF (1 day) hs	2.3	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code

#1MuZeroSOTA
131.13
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#2Agent57
127.32
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#3GDI-H3
113.4
Score· 2022-06-07
Generalized Data Distribution Iteration
#4GDI-I3
108.2
Score· 2022-06-07
Generalized Data Distribution Iteration
#5GDI-I3
108.2
Score· 2022-06-07
Generalized Data Distribution Iteration
#6MuZero (Res2 Adam)
100.59
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#7R2D2
100.4
Score
No paperCode
#8DreamerV2
78
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#9FQFSOTA
75.7
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#10Ape-XSOTA
73.8
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#11Advantage LearningSOTA
69.31
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#12Bootstrapped DQN
66.6
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#13ASL DDQN
65.8
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#14Duel noopSOTA
65.3
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#15DDQN (tuned) noop
65.1
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#16DNA
64.8
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#17DDQN+Pop-Art noop
64.3
Score· 2016-02-24
Learning values across many orders of magnitude
#18NoisyNet-Dueling
64
Score· 2017-06-30
Noisy Networks for Exploration Code
#19DQN noopSOTA
63.9
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#20Prior noop
62.6
Score· 2015-11-18
Prioritized Experience Replay Code
#21IQN
62.5
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#22Duel hs
62
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#23GorilaSOTA
61.8
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#24QR-DQN-1
59.4
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#25DDQN (tuned) hs
59.1
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#26DQN hs
58.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#27Prior hs
56.2
Score· 2015-11-18
Prioritized Experience Replay Code
#28C51 noop
52.3
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#29Nature DQN
51.6
Score
No paperCode
#30UCTSOTA
50.4
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#31A3C FF hs
32.8
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#32Best Learner
28.7
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#33Prior+Duel noop
27.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#34Prior+Duel hs
24.7
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35CGP
24.2
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#36IMPALA (deep)
12.96
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#37SARSA
12.4
Score
No paper
#38ES FF (1 hour) noop
11.9
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#39A2C + SIL
10.5
Score· 2018-06-14
Self-Imitation Learning Code
#40POP3D
4.6
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#41A3C LSTM hs
2.6
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#42A3C FF (1 day) hs
2.3
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code