Video Games on Atari 2600 James Bond

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	620780	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-I3	594500	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-I3	594500	No	Generalized Data Distribution Iteration	2022-06-07	-
4	Agent57	135784.96	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	FQF	87291.7	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
6	MuZero	41063.25	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
7	DreamerV2	40445	No	Mastering Atari with Discrete World Models	2020-10-05	Code
8	IQN	35108	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
9	MuZero (Res2 Adam)	28626.23	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
10	R2D2	25354	No	-	-	Code
11	Ape-X	21322.5	No	Distributed Prioritized Experience Replay	2018-03-02	Code
12	DNA	14102	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
13	CGP	6130	No	Evolving simple programs for playing Atari games	2018-06-14	Code
14	Prior noop	5148	No	Prioritized Experience Replay	2015-11-18	Code
15	QR-DQN-1	4703	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
16	Prior hs	3961	No	Prioritized Experience Replay	2015-11-18	Code
17	ASL DDQN	2237	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
18	C51 noop	1909	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
19	Bootstrapped DQN	1663.5	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
20	DDQN (tuned) noop	1358	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
21	Duel noop	1312.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
22	Recurrent Rational DQN Average	1137	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
23	Rational DQN Average	1122	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
24	Advantage Learning	848.46	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
25	Duel hs	835.5	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
26	Prior+Duel noop	812	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
27	Persistent AL	772.09	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
28	DQN noop	768.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
29	DQN hs	697.5	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
30	A3C LSTM hs	613	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
31	IMPALA (deep)	601.5	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
32	Prior+Duel hs	585	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	Nature DQN	576.7	No	-	-	Code
34	DDQN (tuned) hs	573	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	A3C FF hs	541	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
36	DDQN+Pop-Art noop	507.5	No	Learning values across many orders of magnitude	2016-02-24	-
37	Gorila	444	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
38	POP3D	358.54	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
39	SARSA	354.1	No	-	-	-
40	A3C FF (1 day) hs	351.5	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
41	UCT	330	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	A2C + SIL	310.8	No	Self-Imitation Learning	2018-06-14	Code
43	Best Learner	202.8	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
44	SAC	68.3	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code

#1GDI-H3SOTA
620780
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-I3
594500
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-I3
594500
Score· 2022-06-07
Generalized Data Distribution Iteration
#4Agent57SOTA
135784.96
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#5FQFSOTA
87291.7
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#6MuZero
41063.25
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#7DreamerV2
40445
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#8IQNSOTA
35108
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#9MuZero (Res2 Adam)
28626.23
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#10R2D2
25354
Score
No paperCode
#11Ape-XSOTA
21322.5
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#12DNA
14102
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#13CGP
6130
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#14Prior noopSOTA
5148
Score· 2015-11-18
Prioritized Experience Replay Code
#15QR-DQN-1
4703
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#16Prior hs
3961
Score· 2015-11-18
Prioritized Experience Replay Code
#17ASL DDQN
2237
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#18C51 noop
1909
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#19Bootstrapped DQN
1663.5
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#20DDQN (tuned) noop
1358
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#21Duel noop
1312.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#22Recurrent Rational DQN Average
1137
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#23Rational DQN Average
1122
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#24Advantage Learning
848.46
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#25Duel hs
835.5
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#26Prior+Duel noop
812
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#27Persistent AL
772.09
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#28DQN noopSOTA
768.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#29DQN hs
697.5
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#30A3C LSTM hs
613
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#31IMPALA (deep)
601.5
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#32Prior+Duel hs
585
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33Nature DQN
576.7
Score
No paperCode
#34DDQN (tuned) hs
573
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#35A3C FF hs
541
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#36DDQN+Pop-Art noop
507.5
Score· 2016-02-24
Learning values across many orders of magnitude
#37GorilaSOTA
444
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#38POP3D
358.54
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#39SARSA
354.1
Score
No paper
#40A3C FF (1 day) hs
351.5
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#41UCTSOTA
330
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#42A2C + SIL
310.8
Score· 2018-06-14
Self-Imitation Learning Code
#43Best Learner
202.8
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#44SAC
68.3
Score· 2019-10-16
Soft Actor-Critic for Discrete Action Settings Code