Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Pong dataset and benchmarks · SOTA2 Research

Research Datasets

Pong

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Adversarial Attack

Pong

21Cumulative Reward

80

Adversarial Quality Diversity

Pong

0.641Win Rate

8

Reinforcement Learning

Pong

40Average Reward

8

Single-agent Reinforcement Learning (SARL)

Pong Poisoned

18.2Average Episode Return

7

Single-agent Reinforcement Learning (SARL)

Pong Clean

18.5Average Episode Return

7

Reinforcement Learning

Pong Gymnasium

3Mean Best Reward

5

Reinforcement Learning

Pong Atari 2600 (test)

20Average Total Reward

5

Reinforcement Learning

Pong

3Mean Best Reward

4

Deep Reinforcement Learning

Pong Atari 2600

19.8IQM Return

4

Extrapolation performance

Pong (test)

100Accuracy

4

Policy Imitation

Pong Atari (test)

95Accuracy

4

Reinforcement Learning

Pong (Atari) (unseen states)

18.5Reward

4

Adversarial Detection

Pong Gym Atari (test)

83FGSM

2

Pong 256x256 (test)

100Accuracy (256x256)

2

Pong

1Accuracy

2

Throughput Measurement

Pong

1.4SPS

1

Popular tasks

Reinforcement Learning Extrapolation Single-agent Reinforcement Learning (SARL)Adversarial Attack Adversarial Detection

Follow for updates

Join SOTA2 Contact