| --- |
| library_name: stable-baselines3 |
| tags: |
| - reinforcement-learning |
| - battleship |
| - ppo |
| - maskable-ppo |
| - sb3-contrib |
| - custom-environment |
| --- |
| |
| # Battleship PPO Agent — Hanks1234/battleship-ppo-dagger |
|
|
| A MaskablePPO agent trained on a 10x20 Battleship board with custom |
| T-shaped and Z-shaped ships using [sb3-contrib](https://sb3-contrib.readthedocs.io/). |
|
|
| ## Environment |
|
|
| - **Board**: 10 columns x 20 rows |
| - **Ships**: 10 ships including T-shaped Battleships and Z-shaped Carriers |
| - **Observation**: 5-channel binary image (5, 20, 10) |
| - **Action**: Discrete(200) with action masking (no repeat shots) |
|
|
| ## Training Config |
|
|
| | Parameter | Value | |
| |-----------|-------| |
| | `method` | `DAgger (Dataset Aggregation)` | |
| | `base_model` | `BC-pretrained MaskablePPO` | |
| | `observation_channels` | `15` | |
| | `board_size` | `10x20` | |
| | `expert` | `Monte Carlo solver (1000 samples)` | |
| | `disagree_only` | `True` | |
| | `confidence_threshold` | `0.3` | |
| | `freeze_cnn` | `True` | |
|
|
| ## Evaluation Results |
|
|
| | Metric | Value | |
| |--------|-------| |
| | mean_shots_500_games | 100.90 | |
| | verified_games | 500 | |
| | seed | 20000 | |
| | notes | 15-channel DAgger; first model to break 100-shot barrier | |
|
|
| ## Usage |
|
|
| ```python |
| from training.hub import load_model_from_hub |
| |
| model = load_model_from_hub("Hanks1234/battleship-ppo-dagger") |
| ``` |
|
|
