Research Article
A Study on the Agent in Fighting Games Based on Deep Reinforcement Learning
| Hyper parameter | Value |
| Mini-batch size | 100 | Replay memory size | 40000 | Target network update frequency (round) | 4 | Discount factor | 0.95 | Initial exploration | 1.0 | Final exploration | 0.49 | Image size | 224 |
|
|