Atari Games on Atari 2600 Chopper Command

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	999999	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-I3	999999	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-H3	999999	No	Generalized Data Distribution Iteration	2022-06-07	-
4	Agent57	999900	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	MuZero	991039.7	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	R2D2	986652	No	-	-	Code
7	FQF	876460	No	Fully Parameterized Quantile Function for Distri...	2019-11-05	Code
8	Ape-X	721851	No	Distributed Prioritized Experience Replay	2018-03-02	Code
9	Reactor 500M	107779	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
10	UCT	34018.8	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
11	DNA	31181	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
12	IMPALA (deep)	28255	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
13	IQN	16836	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	C51 noop	15600	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
15	ASL DDQN	15071	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
16	QR-DQN-1	14667	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
17	Prior+Duel noop	13185	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	NoisyNet-Dueling	11477	No	Noisy Networks for Exploration	2017-06-30	Code
19	Duel noop	11215	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
20	A3C LSTM hs	10150	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
21	Prior noop	8600	No	Prioritized Experience Replay	2015-11-18	Code
22	Prior+Duel hs	8058	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
23	A3C FF hs	7021	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
24	A2C + SIL	6710	No	Self-Imitation Learning	2018-06-14	Code
25	Nature DQN	6687	No	-	-	Code
26	POP3D	6308.33	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
27	DQN noop	6126	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
28	MuZero (Res2 Adam)	5989.55	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
29	DDQN (tuned) noop	5809	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
30	Persistent AL	5734.93	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
31	Advantage Learning	5431.36	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
32	DQN hs	5017	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
33	A3C FF (1 day) hs	4669	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
34	Prior hs	4635	No	Prioritized Experience Replay	2015-11-18	Code
35	Bootstrapped DQN	4100	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
36	Duel hs	3784	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
37	ES FF (1 hour) noop	3710	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
38	CGP	3580	No	Evolving simple programs for playing Atari games	2018-06-14	Code
39	DDQN (tuned) hs	3495	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
40	Gorila	3191.8	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
41	DreamerV2	2861	No	Mastering Atari with Discrete World Models	2020-10-05	Code
42	Best Learner	1581.5	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
43	CURL	1198	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
44	DDQN+Pop-Art noop	775	No	Learning values across many orders of magnitude	2016-02-24	-
45	SARSA	16.9	No	-	-	-

#1GDI-H3SOTA
999999
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-I3
999999
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-H3
999999
Score· 2022-06-07
Generalized Data Distribution Iteration
#4Agent57SOTA
999900
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#5MuZeroSOTA
991039.7
Score· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model Code
#6R2D2
986652
Score
No paperCode
#7FQFSOTA
876460
Score· 2019-11-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning Code
#8Ape-XSOTA
721851
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#9Reactor 500MSOTA
107779
Score· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#10UCTSOTA
34018.8
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#11DNA
31181
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#12IMPALA (deep)
28255
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#13IQN
16836
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#14C51 noop
15600
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#15ASL DDQN
15071
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#16QR-DQN-1
14667
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#17Prior+Duel noop
13185
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18NoisyNet-Dueling
11477
Score· 2017-06-30
Noisy Networks for Exploration Code
#19Duel noop
11215
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#20A3C LSTM hs
10150
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#21Prior noop
8600
Score· 2015-11-18
Prioritized Experience Replay Code
#22Prior+Duel hs
8058
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#23A3C FF hs
7021
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#24A2C + SIL
6710
Score· 2018-06-14
Self-Imitation Learning Code
#25Nature DQN
6687
Score
No paperCode
#26POP3D
6308.33
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#27DQN noop
6126
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#28MuZero (Res2 Adam)
5989.55
Score· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model Code
#29DDQN (tuned) noop
5809
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#30Persistent AL
5734.93
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#31Advantage Learning
5431.36
Score· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning Code
#32DQN hs
5017
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#33A3C FF (1 day) hs
4669
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#34Prior hs
4635
Score· 2015-11-18
Prioritized Experience Replay Code
#35Bootstrapped DQN
4100
Score· 2016-02-15
Deep Exploration via Bootstrapped DQN Code
#36Duel hs
3784
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#37ES FF (1 hour) noop
3710
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#38CGP
3580
Score· 2018-06-14
Evolving simple programs for playing Atari games Code
#39DDQN (tuned) hs
3495
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#40Gorila
3191.8
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#41DreamerV2
2861
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#42Best Learner
1581.5
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#43CURL
1198
Score· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning Code
#44DDQN+Pop-Art noop
775
Score· 2016-02-24
Learning values across many orders of magnitude
#45SARSA
16.9
Score
No paper