Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Playing Games
/
Video Games
/
Atari 2600 Up and Down
Video Games on Atari 2600 Up and Down
Metric: Score (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Score (best first)
Score (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Score
▼
Extra Data
Paper
Date
↕
Code
1
GDI-I3
986440
No
Generalized Data Distribution Iteration
2022-06-07
-
2
GDI-I3
986440
No
Generalized Data Distribution Iteration
2022-06-07
-
3
GDI-H3
966590
No
Generalized Data Distribution Iteration
2022-06-07
-
4
MuZero
715545.61
No
Mastering Atari, Go, Chess and Shogi by Planning...
2019-11-19
Code
5
DreamerV2
653662
No
Mastering Atari with Discrete World Models
2020-10-05
Code
6
MuZero (Res2 Adam)
634898.18
No
Online and Offline Reinforcement Learning by Pla...
2021-04-13
Code
7
Agent57
623805.73
No
Agent57: Outperforming the Atari Human Benchmark
2020-03-30
Code
8
R2D2
589226.9
No
-
-
Code
9
Ape-X
401884.3
No
Distributed Prioritized Experience Replay
2018-03-02
Code
10
RIMs-PPO
390000
No
Recurrent Independent Mechanisms
2019-09-24
Code
11
IMPALA (deep)
332546.75
No
IMPALA: Scalable Distributed Deep-RL with Import...
2018-02-05
Code
12
DNA
291934
No
DNA: Proximal Policy Optimization with a Dual Ne...
2022-06-20
Code
13
POP3D
242701.51
No
Policy Optimization With Penalized Point Probabi...
2018-07-02
Code
14
A3C LSTM hs
105728.7
No
Asynchronous Methods for Deep Reinforcement Lear...
2016-02-04
Code
15
IQN
88148
No
Implicit Quantile Networks for Distributional Re...
2018-06-14
Code
16
A3C FF hs
74705.7
No
Asynchronous Methods for Deep Reinforcement Lear...
2016-02-04
Code
17
UCT
74473.6
No
The Arcade Learning Environment: An Evaluation P...
2012-07-19
Code
18
QR-DQN-1
71260
No
Distributional Reinforcement Learning with Quant...
2017-10-27
Code
19
ES FF (1 hour) noop
67974
No
Evolution Strategies as a Scalable Alternative t...
2017-03-10
Code
20
NoisyNet-Dueling
61326
No
Noisy Networks for Exploration
2017-06-30
Code
21
A3C FF (1 day) hs
54525.4
No
Asynchronous Methods for Deep Reinforcement Lear...
2016-02-04
Code
22
A2C + SIL
53314.6
No
Self-Imitation Learning
2018-06-14
Code
23
Duel noop
44939.6
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
24
Prior+Duel noop
33879.1
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
25
Bootstrapped DQN
26231
No
Deep Exploration via Bootstrapped DQN
2016-02-15
Code
26
ASL DDQN
25127.4
No
Train a Real-world Local Path Planner in One Hou...
2023-05-07
Code
27
Duel hs
24759.2
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
28
DDQN (tuned) noop
22972.2
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
29
Prior+Duel hs
22681.3
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
30
DDQN+Pop-Art noop
22474.4
No
Learning values across many orders of magnitude
2016-02-24
-
31
DDQN (tuned) hs
19086.9
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
32
Prior noop
16154.1
No
Prioritized Experience Replay
2015-11-18
Code
33
C51 noop
15612
No
A Distributional Perspective on Reinforcement Le...
2017-07-21
Code
34
CGP
14524
No
Evolving simple programs for playing Atari games
2018-06-14
Code
35
Advantage Learning
13909.74
No
Increasing the Action Gap: New Operators for Rei...
2015-12-15
Code
36
Prior hs
12157.4
No
Prioritized Experience Replay
2015-11-18
Code
37
DQN noop
9989.9
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
38
Gorila
8747.7
No
Massively Parallel Methods for Deep Reinforcemen...
2015-07-15
Code
39
Nature DQN
8456
No
-
-
Code
40
DQN hs
8038.5
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
41
Best Learner
3532.7
No
The Arcade Learning Environment: An Evaluation P...
2012-07-19
Code
42
CURL
2735.2
No
CURL: Contrastive Unsupervised Representations f...
2020-04-08
Code
43
SARSA
2449
No
-
-
-
44
SAC
250.7
No
Soft Actor-Critic for Discrete Action Settings
2019-10-16
Code
#1
GDI-I3
SOTA
986440
Score
· 2022-06-07
Generalized Data Distribution Iteration
#2
GDI-I3
986440
Score
· 2022-06-07
Generalized Data Distribution Iteration
#3
GDI-H3
966590
Score
· 2022-06-07
Generalized Data Distribution Iteration
#4
MuZero
SOTA
715545.61
Score
· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Code
#5
DreamerV2
653662
Score
· 2020-10-05
Mastering Atari with Discrete World Models
Code
#6
MuZero (Res2 Adam)
634898.18
Score
· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model
Code
#7
Agent57
623805.73
Score
· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark
Code
#8
R2D2
589226.9
Score
No paper
Code
#9
Ape-X
SOTA
401884.3
Score
· 2018-03-02
Distributed Prioritized Experience Replay
Code
#10
RIMs-PPO
390000
Score
· 2019-09-24
Recurrent Independent Mechanisms
Code
#11
IMPALA (deep)
SOTA
332546.75
Score
· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Code
#12
DNA
291934
Score
· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture
Code
#13
POP3D
242701.51
Score
· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Code
#14
A3C LSTM hs
SOTA
105728.7
Score
· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Code
#15
IQN
88148
Score
· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning
Code
#16
A3C FF hs
74705.7
Score
· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Code
#17
UCT
SOTA
74473.6
Score
· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents
Code
#18
QR-DQN-1
71260
Score
· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression
Code
#19
ES FF (1 hour) noop
67974
Score
· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Code
#20
NoisyNet-Dueling
61326
Score
· 2017-06-30
Noisy Networks for Exploration
Code
#21
A3C FF (1 day) hs
54525.4
Score
· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Code
#22
A2C + SIL
53314.6
Score
· 2018-06-14
Self-Imitation Learning
Code
#23
Duel noop
44939.6
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#24
Prior+Duel noop
33879.1
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#25
Bootstrapped DQN
26231
Score
· 2016-02-15
Deep Exploration via Bootstrapped DQN
Code
#26
ASL DDQN
25127.4
Score
· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Code
#27
Duel hs
24759.2
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#28
DDQN (tuned) noop
22972.2
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#29
Prior+Duel hs
22681.3
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#30
DDQN+Pop-Art noop
22474.4
Score
· 2016-02-24
Learning values across many orders of magnitude
#31
DDQN (tuned) hs
19086.9
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#32
Prior noop
16154.1
Score
· 2015-11-18
Prioritized Experience Replay
Code
#33
C51 noop
15612
Score
· 2017-07-21
A Distributional Perspective on Reinforcement Learning
Code
#34
CGP
14524
Score
· 2018-06-14
Evolving simple programs for playing Atari games
Code
#35
Advantage Learning
13909.74
Score
· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning
Code
#36
Prior hs
12157.4
Score
· 2015-11-18
Prioritized Experience Replay
Code
#37
DQN noop
9989.9
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#38
Gorila
8747.7
Score
· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning
Code
#39
Nature DQN
8456
Score
No paper
Code
#40
DQN hs
8038.5
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#41
Best Learner
3532.7
Score
· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents
Code
#42
CURL
2735.2
Score
· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Code
#43
SARSA
2449
Score
No paper
#44
SAC
250.7
Score
· 2019-10-16
Soft Actor-Critic for Discrete Action Settings
Code