Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Playing Games
/
Video Games
/
Atari 2600 Boxing
Video Games on Atari 2600 Boxing
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
MuZero
100
No
Mastering Atari, Go, Chess and Shogi by Planning...
2019-11-19
Code
2
Ape-X
100
No
Distributed Prioritized Experience Replay
2018-03-02
Code
3
NoisyNet-Dueling
100
No
Noisy Networks for Exploration
2017-06-30
Code
4
UCT
100
No
The Arcade Learning Environment: An Evaluation P...
2012-07-19
Code
5
Agent57
100
No
Agent57: Outperforming the Atari Human Benchmark
2020-03-30
Code
6
MuZero (Res2 Adam)
100
No
Online and Offline Reinforcement Learning by Pla...
2021-04-13
Code
7
GDI-H3
100
No
Generalized Data Distribution Iteration
2022-06-07
-
8
GDI-I3
100
No
Generalized Data Distribution Iteration
2022-06-07
-
9
GDI-H3
100
No
Generalized Data Distribution Iteration
2022-06-07
-
10
IMPALA (deep)
99.96
No
IMPALA: Scalable Distributed Deep-RL with Import...
2018-02-05
Code
11
QR-DQN-1
99.9
No
Distributional Reinforcement Learning with Quant...
2017-10-27
Code
12
DNA
99.9
No
DNA: Proximal Policy Optimization with a Dual Ne...
2022-06-20
Code
13
IQN
99.8
No
Implicit Quantile Networks for Distributional Re...
2018-06-14
Code
14
A2C + SIL
99.6
No
Self-Imitation Learning
2018-06-14
Code
15
ASL DDQN
99.6
No
Train a Real-world Local Path Planner in One Hou...
2023-05-07
Code
16
Duel noop
99.4
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
17
Reactor 500M
99.4
No
The Reactor: A fast and sample-efficient Actor-C...
2017-04-15
-
18
DDQN+Pop-Art noop
99.3
No
Learning values across many orders of magnitude
2016-02-24
-
19
Prior+Duel noop
98.9
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
20
R2D2
98.5
No
-
-
Code
21
DDRL A3C
98
No
Distributed Deep Reinforcement Learning: Learn h...
2018-01-09
Code
22
C51 noop
97.8
No
A Distributional Perspective on Reinforcement Le...
2017-07-21
Code
23
POP3D
97.23
No
Policy Optimization With Penalized Point Probabi...
2018-07-02
Code
24
Prior noop
95.6
No
Prioritized Experience Replay
2015-11-18
Code
25
Persistent AL
94.3
No
Increasing the Action Gap: New Operators for Rei...
2015-12-15
Code
26
Advantage Learning
93.94
No
Increasing the Action Gap: New Operators for Rei...
2015-12-15
Code
27
Bootstrapped DQN
93.2
No
Deep Exploration via Bootstrapped DQN
2016-02-15
Code
28
DreamerV2
92
No
Mastering Atari with Discrete World Models
2020-10-05
Code
29
DDQN (tuned) noop
91.6
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
30
DQN noop
88
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
31
Prior+Duel hs
79.2
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
32
Duel hs
77.3
No
Dueling Network Architectures for Deep Reinforce...
2015-11-20
Code
33
Gorila
74.2
No
Massively Parallel Methods for Deep Reinforcemen...
2015-07-15
Code
34
DDQN (tuned) hs
73.5
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
35
Prior hs
72.3
No
Prioritized Experience Replay
2015-11-18
Code
36
Nature DQN
71.8
No
-
-
Code
37
DQN hs
70.3
No
Deep Reinforcement Learning with Double Q-learning
2015-09-22
Code
38
A3C FF hs
59.8
No
Asynchronous Methods for Deep Reinforcement Lear...
2016-02-04
Code
39
ES FF (1 hour) noop
49.8
No
Evolution Strategies as a Scalable Alternative t...
2017-03-10
Code
40
Best Learner
44
No
The Arcade Learning Environment: An Evaluation P...
2012-07-19
Code
41
CGP
38.4
No
Evolving simple programs for playing Atari games
2018-06-14
Code
42
A3C LSTM hs
37.3
No
Asynchronous Methods for Deep Reinforcement Lear...
2016-02-04
Code
43
A3C FF (1 day) hs
33.7
No
Asynchronous Methods for Deep Reinforcement Lear...
2016-02-04
Code
44
SARSA
9.8
No
-
-
-
45
CURL
4.8
No
CURL: Contrastive Unsupervised Representations f...
2020-04-08
Code
#1
MuZero
100
Score
· 2019-11-19
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Code
#2
Ape-X
100
Score
· 2018-03-02
Distributed Prioritized Experience Replay
Code
#3
NoisyNet-Dueling
100
Score
· 2017-06-30
Noisy Networks for Exploration
Code
#4
UCT
SOTA
100
Score
· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents
Code
#5
Agent57
100
Score
· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark
Code
#6
MuZero (Res2 Adam)
100
Score
· 2021-04-13
Online and Offline Reinforcement Learning by Planning with a Learned Model
Code
#7
GDI-H3
100
Score
· 2022-06-07
Generalized Data Distribution Iteration
#8
GDI-I3
100
Score
· 2022-06-07
Generalized Data Distribution Iteration
#9
GDI-H3
100
Score
· 2022-06-07
Generalized Data Distribution Iteration
#10
IMPALA (deep)
99.96
Score
· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Code
#11
QR-DQN-1
99.9
Score
· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression
Code
#12
DNA
99.9
Score
· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture
Code
#13
IQN
99.8
Score
· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning
Code
#14
A2C + SIL
99.6
Score
· 2018-06-14
Self-Imitation Learning
Code
#15
ASL DDQN
99.6
Score
· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Code
#16
Duel noop
99.4
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#17
Reactor 500M
99.4
Score
· 2017-04-15
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
#18
DDQN+Pop-Art noop
99.3
Score
· 2016-02-24
Learning values across many orders of magnitude
#19
Prior+Duel noop
98.9
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#20
R2D2
98.5
Score
No paper
Code
#21
DDRL A3C
98
Score
· 2018-01-09
Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes
Code
#22
C51 noop
97.8
Score
· 2017-07-21
A Distributional Perspective on Reinforcement Learning
Code
#23
POP3D
97.23
Score
· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Code
#24
Prior noop
95.6
Score
· 2015-11-18
Prioritized Experience Replay
Code
#25
Persistent AL
94.3
Score
· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning
Code
#26
Advantage Learning
93.94
Score
· 2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning
Code
#27
Bootstrapped DQN
93.2
Score
· 2016-02-15
Deep Exploration via Bootstrapped DQN
Code
#28
DreamerV2
92
Score
· 2020-10-05
Mastering Atari with Discrete World Models
Code
#29
DDQN (tuned) noop
91.6
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#30
DQN noop
88
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#31
Prior+Duel hs
79.2
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#32
Duel hs
77.3
Score
· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning
Code
#33
Gorila
74.2
Score
· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning
Code
#34
DDQN (tuned) hs
73.5
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#35
Prior hs
72.3
Score
· 2015-11-18
Prioritized Experience Replay
Code
#36
Nature DQN
71.8
Score
No paper
Code
#37
DQN hs
70.3
Score
· 2015-09-22
Deep Reinforcement Learning with Double Q-learning
Code
#38
A3C FF hs
59.8
Score
· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Code
#39
ES FF (1 hour) noop
49.8
Score
· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Code
#40
Best Learner
44
Score
· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents
Code
#41
CGP
38.4
Score
· 2018-06-14
Evolving simple programs for playing Atari games
Code
#42
A3C LSTM hs
37.3
Score
· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Code
#43
A3C FF (1 day) hs
33.7
Score
· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning
Code
#44
SARSA
9.8
Score
No paper
#45
CURL
4.8
Score
· 2020-04-08
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Code