Video Games on Atari 2600 Wizard of Wor

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	MuZero	197126	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
2	Agent57	157306.41	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
3	R2D2	144362.7	No	-	-	Code
4	UCT	105500	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
5	MuZero (Res2 Adam)	100096.6	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
6	GDI-I3	64239	No	Generalized Data Distribution Iteration	2022-06-07	-
7	GDI-H3	63735	No	Generalized Data Distribution Iteration	2022-06-07	-
8	Ape-X	46204	No	Distributed Prioritized Experience Replay	2018-03-02	Code
9	FQF	44782.6	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
10	IQN	31190	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
11	QR-DQN-1	25061	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
12	ASL DDQN	21049	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
13	DNA	20851	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
14	A3C LSTM hs	18082	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
15	A3C FF hs	17244	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
16	DreamerV2	12851	No	Mastering Atari with Discrete World Models	2020-10-05	Code
17	Prior+Duel noop	12352	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	Prior+Duel hs	10471	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
19	Gorila	10431	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
20	Advantage Learning	9541.14	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
21	C51 noop	9300	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
22	IMPALA (deep)	9157.5	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
23	NoisyNet-Dueling	9149	No	Noisy Networks for Exploration	2017-06-30	Code
24	Duel noop	7855	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
25	DDQN (tuned) noop	7492	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
26	A2C + SIL	7088.3	No	Self-Imitation Learning	2018-06-14	Code
27	Duel hs	7054	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
28	Bootstrapped DQN	6804.7	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
29	DDQN (tuned) hs	6201	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
30	Prior hs	5727	No	Prioritized Experience Replay	2015-11-18	Code
31	A3C FF (1 day) hs	5278	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
32	Prior noop	4802	No	Prioritized Experience Replay	2015-11-18	Code
33	POP3D	4704	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
34	CGP	3820	No	Evolving simple programs for playing Atari games	2018-06-14	Code
35	ES FF (1 hour) noop	3480	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
36	Nature DQN	3393	No	-	-	Code
37	DQN noop	2704	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	Best Learner	1981.3	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
39	DQN hs	1609	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
40	DDQN+Pop-Art noop	483	No	Learning values across many orders of magnitude	2016-02-24	-
41	SARSA	36.9	No	-	-	-

#1MuZeroSOTA
197126
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#2Agent57
157306.41
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#3R2D2
144362.7
Score
No paperCode
#4UCTSOTA
105500
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#5MuZero (Res2 Adam)
100096.6
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#6GDI-I3
64239
Score· 2022-06-07
Generalized Data Distribution Iteration
#7GDI-H3
63735
Score· 2022-06-07
Generalized Data Distribution Iteration
#8Ape-X
46204
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#9FQF
44782.6
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#10IQN
31190
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#11QR-DQN-1
25061
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#12ASL DDQN
21049
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#13DNA
20851
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#14A3C LSTM hs
18082
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#15A3C FF hs
17244
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#16DreamerV2
12851
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#17Prior+Duel noop
12352
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18Prior+Duel hs
10471
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#19Gorila
10431
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#20Advantage Learning
9541.14
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#21C51 noop
9300
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#22IMPALA (deep)
9157.5
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#23NoisyNet-Dueling
9149
Score· 2017-06-30
Noisy Networks for Exploration Code
#24Duel noop
7855
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#25DDQN (tuned) noop
7492
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#26A2C + SIL
7088.3
Score· 2018-06-14
Self-Imitation Learning Code
#27Duel hs
7054
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#28Bootstrapped DQN
6804.7
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#29DDQN (tuned) hs
6201
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#30Prior hs
5727
Score· 2015-11-18
Prioritized Experience Replay Code
#31A3C FF (1 day) hs
5278
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#32Prior noop
4802
Score· 2015-11-18
Prioritized Experience Replay Code
#33POP3D
4704
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#34CGP
3820
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#35ES FF (1 hour) noop
3480
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#36Nature DQN
3393
Score
No paperCode
#37DQN noop
2704
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38Best Learner
1981.3
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#39DQN hs
1609
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#40DDQN+Pop-Art noop
483
Score· 2016-02-24
Learning values across many orders of magnitude
#41SARSA
36.9
Score
No paper