summary.md

# Experiment Summary

## Supervised

| run | model | hidden | lr | epochs | final_val_opt_gap | best_val_opt_gap | final_val_exact | best_val_exact |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| cnn_h128-64_lr0.001 | cnn | 128,64 | 0.001 | 5 | 0.6025 | 0.6025 | 0.4403 | 0.4403 |
| mlp_h128-64_lr0.001 | mlp | 128,64 | 0.001 | 5 | 0.1741 | 0.1701 | 0.8921 | 0.8921 |
| vector_h128-64_lr0.001 | vector | 128,64 | 0.001 | 5 | 0.0681 | 0.0681 | 0.9995 | 0.9995 |

## RL

| run | algo | hidden | episodes | final_reward_ma | opt_gap_ep200 | opt_gap_ep500 | final_opt_gap | best_opt_gap | avg_opt_gap |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ppo_h64-32_ep500 | ppo | 64,32 | 500 | -0.0956 | 0.1053 | 0.0949 | 0.0949 | 0.0902 | 0.2247 |
| rl_h64-32_ep500 | rl | 64,32 | 500 | -0.8185 | 1.2689 | 0.6225 | 0.6225 | 0.5287 | 0.9880 |