Atari Games on Atari 2600 Ice Hockey

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	481.9	No	Generalized Data Distribution Iteration	2022-06-07	-
2	R2D2	79.3	No	-	-	Code
3	MuZero	67.04	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
4	Agent57	63.64	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	GDI-I3	44.94	No	Generalized Data Distribution Iteration	2022-06-07	-
6	GDI-I3	44.94	No	Generalized Data Distribution Iteration	2022-06-07	-
7	MuZero (Res2 Adam)	41.66	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
8	UCT	39.4	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
9	Ape-X	33	No	Distributed Prioritized Experience Replay	2018-03-02	Code
10	DreamerV2	26	No	Mastering Atari with Discrete World Models	2020-10-05	Code
11	FQF	17.3	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
12	DNA	7.2	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
13	CGP	4	No	Evolving simple programs for playing Atari games	2018-06-14	Code
14	IMPALA (deep)	3.48	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
15	NoisyNet-Dueling	3	No	Noisy Networks for Exploration	2017-06-30	Code
16	Prior noop	1.3	No	Prioritized Experience Replay	2015-11-18	Code
17	Duel noop	0.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	Prior+Duel hs	0.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
19	IQN	0.2	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
20	Prior hs	-0.2	No	Prioritized Experience Replay	2015-11-18	Code
21	Persistent AL	-0.25	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
22	Prior+Duel noop	-0.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
23	Advantage Learning	-1.24	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
24	Duel hs	-1.3	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
25	Bootstrapped DQN	-1.3	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
26	Nature DQN	-1.6	No	-	-	Code
27	DQN hs	-1.6	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
28	Gorila	-1.7	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
29	A3C LSTM hs	-1.7	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
30	QR-DQN-1	-1.7	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
31	DQN noop	-1.9	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
32	A2C + SIL	-2.4	No	Self-Imitation Learning	2018-06-14	Code
33	DDQN (tuned) hs	-2.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
34	DDQN (tuned) noop	-2.7	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
35	A3C FF hs	-2.8	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
36	SARSA	-3.2	No	-	-	-
37	C51 noop	-3.5	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
38	ASL DDQN	-3.6	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
39	DDQN+Pop-Art noop	-4.1	No	Learning values across many orders of magnitude	2016-02-24	-
40	ES FF (1 hour) noop	-4.1	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
41	POP3D	-4.12	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
42	A3C FF (1 day) hs	-4.7	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
43	Best Learner	-9.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code

#1GDI-H3SOTA
481.9
Score· 2022-06-07
Generalized Data Distribution Iteration
#2R2D2
79.3
Score
No paperCode
#3MuZeroSOTA
67.04
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#4Agent57
63.64
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#5GDI-I3
44.94
Score· 2022-06-07
Generalized Data Distribution Iteration
#6GDI-I3
44.94
Score· 2022-06-07
Generalized Data Distribution Iteration
#7MuZero (Res2 Adam)
41.66
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#8UCTSOTA
39.4
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#9Ape-X
33
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#10DreamerV2
26
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#11FQF
17.3
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#12DNA
7.2
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#13CGP
4
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#14IMPALA (deep)
3.48
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#15NoisyNet-Dueling
3
Score· 2017-06-30
Noisy Networks for Exploration Code
#16Prior noop
1.3
Score· 2015-11-18
Prioritized Experience Replay Code
#17Duel noop
0.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18Prior+Duel hs
0.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#19IQN
0.2
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#20Prior hs
-0.2
Score· 2015-11-18
Prioritized Experience Replay Code
#21Persistent AL
-0.25
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#22Prior+Duel noop
-0.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#23Advantage Learning
-1.24
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#24Duel hs
-1.3
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#25Bootstrapped DQN
-1.3
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#26Nature DQN
-1.6
Score
No paperCode
#27DQN hs
-1.6
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#28Gorila
-1.7
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#29A3C LSTM hs
-1.7
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#30QR-DQN-1
-1.7
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#31DQN noop
-1.9
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#32A2C + SIL
-2.4
Score· 2018-06-14
Self-Imitation Learning Code
#33DDQN (tuned) hs
-2.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#34DDQN (tuned) noop
-2.7
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#35A3C FF hs
-2.8
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#36SARSA
-3.2
Score
No paper
#37C51 noop
-3.5
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#38ASL DDQN
-3.6
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#39DDQN+Pop-Art noop
-4.1
Score· 2016-02-24
Learning values across many orders of magnitude
#40ES FF (1 hour) noop
-4.1
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#41POP3D
-4.12
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#42A3C FF (1 day) hs
-4.7
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#43Best Learner
-9.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code