Hardware: Google Colab T4
| Animal Type | Model Type | Average Reward | Training Time | Total Training Steps |
|---|---|---|---|---|
| Basic Dinosaur | PPO | 319.94 | 1:29:43 | 2,600,000 |
| Basic Dinosaur | SAC | 3091.31 | 4:36:59 | 3,600,000 |
| Trex | PPO | 5,000,000 | ||
| Trex | SAC | 5,000,000 | ||
| Velociraptor | PPO | 5,000,000 | ||
| Velociraptor | SAC | 5,000,000 |