Atari Games on Atari 2600 Kangaroo

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	Agent57	24034.16	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
2	MuZero	16763.6	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
3	Prior noop	16200	No	Prioritized Experience Replay	2015-11-18	Code
4	IQN	15487	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
5	QR-DQN-1	15356	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
6	NoisyNet-Dueling	15227	No	Noisy Networks for Exploration	2017-06-30	Code
7	Bootstrapped DQN	14862.5	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
8	Duel noop	14854	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
9	GDI-H3	14636	No	Generalized Data Distribution Iteration	2022-06-07	-
10	GDI-I3	14500	No	Generalized Data Distribution Iteration	2022-06-07	-
11	GDI-I3	14500	No	Generalized Data Distribution Iteration	2022-06-07	-
12	DNA	14373	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
13	R2D2	14130.7	No	-	-	Code
14	DreamerV2	14064	No	Mastering Atari with Discrete World Models	2020-10-05	Code
15	MuZero (Res2 Adam)	13838	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
16	DDQN+Pop-Art noop	13150	No	Learning values across many orders of magnitude	2016-02-24	-
17	ASL DDQN	13027	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
18	DDQN (tuned) noop	12992	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
19	C51 noop	12853	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
20	Prior hs	12185	No	Prioritized Experience Replay	2015-11-18	Code
21	Persistent AL	11478.46	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
22	DDQN (tuned) hs	11204	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
23	ES FF (1 hour) noop	11200	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
24	Advantage Learning	10809.16	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
25	Duel hs	10334	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
26	DQN noop	7259	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
27	Nature DQN	6740	No	-	-	Code
28	Recurrent Rational DQN Average	5266	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
29	DQN hs	4496	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
30	POP3D	3891.67	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
31	Rational DQN Average	2941	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
32	A2C + SIL	2888.3	No	Self-Imitation Learning	2018-06-14	Code
33	UCT	1990	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
34	Prior+Duel noop	1792	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
35	IMPALA (deep)	1632	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
36	Best Learner	1622.1	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
37	Gorila	1431	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
38	Ape-X	1416	No	Distributed Prioritized Experience Replay	2018-03-02	Code
39	CGP	1400	No	Evolving simple programs for playing Atari games	2018-06-14	Code
40	IDVQ + DRSC + XNES	1200	No	Playing Atari with Six Neurons	2018-06-04	Code
41	Prior+Duel hs	861	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
42	CURL	345.3	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
43	A3C LSTM hs	125	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
44	A3C FF (1 day) hs	106	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
45	A3C FF hs	94	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
46	SAC	29.3	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code
47	SARSA	8.8	No	-	-	-

#1Agent57SOTA
24034.16
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#2MuZeroSOTA
16763.6
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#3Prior noopSOTA
16200
Score· 2015-11-18
Prioritized Experience Replay Code
#4IQN
15487
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#5QR-DQN-1
15356
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#6NoisyNet-Dueling
15227
Score· 2017-06-30
Noisy Networks for Exploration Code
#7Bootstrapped DQN
14862.5
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#8Duel noop
14854
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#9GDI-H3
14636
Score· 2022-06-07
Generalized Data Distribution Iteration
#10GDI-I3
14500
Score· 2022-06-07
Generalized Data Distribution Iteration
#11GDI-I3
14500
Score· 2022-06-07
Generalized Data Distribution Iteration
#12DNA
14373
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#13R2D2
14130.7
Score
No paperCode
#14DreamerV2
14064
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#15MuZero (Res2 Adam)
13838
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#16DDQN+Pop-Art noop
13150
Score· 2016-02-24
Learning values across many orders of magnitude
#17ASL DDQN
13027
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#18DDQN (tuned) noop
12992
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#19C51 noop
12853
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#20Prior hs
12185
Score· 2015-11-18
Prioritized Experience Replay Code
#21Persistent AL
11478.46
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#22DDQN (tuned) hsSOTA
11204
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#23ES FF (1 hour) noop
11200
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#24Advantage Learning
10809.16
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#25Duel hs
10334
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#26DQN noop
7259
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#27Nature DQN
6740
Score
No paperCode
#28Recurrent Rational DQN Average
5266
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#29DQN hs
4496
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#30POP3D
3891.67
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#31Rational DQN Average
2941
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#32A2C + SIL
2888.3
Score· 2018-06-14
Self-Imitation Learning Code
#33UCTSOTA
1990
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#34Prior+Duel noop
1792
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#35IMPALA (deep)
1632
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#36Best Learner
1622.1
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#37Gorila
1431
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#38Ape-X
1416
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#39CGP
1400
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#40IDVQ + DRSC + XNES
1200
Score· 2018-06-04
Playing Atari with Six Neurons Code
#41Prior+Duel hs
861
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#42CURL
345.3
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#43A3C LSTM hs
125
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#44A3C FF (1 day) hs
106
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#45A3C FF hs
94
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#46SAC
29.3
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code
#47SARSA
8.8
Score
No paper