Pong
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Adversarial Attack | Pong | Cumulative Reward21 | 80 | |
| Adversarial Quality Diversity | Pong | Win Rate0.641 | 8 | |
| Reinforcement Learning | Pong | Average Reward40 | 8 | |
| Single-agent Reinforcement Learning (SARL) | Pong Poisoned | Average Episode Return18.2 | 7 | |
| Single-agent Reinforcement Learning (SARL) | Pong Clean | Average Episode Return18.5 | 7 | |
| Reinforcement Learning | Pong Gymnasium | Mean Best Reward3 | 5 | |
| Reinforcement Learning | Pong Atari 2600 (test) | Average Total Reward20 | 5 | |
| Reinforcement Learning | Pong | Mean Best Reward3 | 4 | |
| Deep Reinforcement Learning | Pong Atari 2600 | IQM Return19.8 | 4 | |
| Extrapolation performance | Pong (test) | Accuracy100 | 4 | |
| Policy Imitation | Pong Atari (test) | Accuracy95 | 4 | |
| Reinforcement Learning | Pong (Atari) (unseen states) | Reward18.5 | 4 | |
| Adversarial Detection | Pong Gym Atari (test) | FGSM83 | 2 | |
| Extrapolation | Pong 256x256 (test) | Accuracy (256x256)100 | 2 | |
| Extrapolation | Pong | Accuracy1 | 2 | |
| Throughput Measurement | Pong | SPS1.4 | 1 |
Showing 16 of 16 rows