| { | |
| "env_id": "Taxi-v3", | |
| "max_steps": 99, | |
| "n_training_episodes": 25000, | |
| "n_eval_episodes": 100, | |
| "eval_seed": [ | |
| 16, | |
| 54, | |
| 165, | |
| 177, | |
| 191, | |
| 191, | |
| 120, | |
| 80, | |
| 149, | |
| 178, | |
| 48, | |
| 38, | |
| 6, | |
| 125, | |
| 174, | |
| 73, | |
| 50, | |
| 172, | |
| 100, | |
| 148, | |
| 146, | |
| 6, | |
| 25, | |
| 40, | |
| 68, | |
| 148, | |
| 49, | |
| 167, | |
| 9, | |
| 97, | |
| 164, | |
| 176, | |
| 61, | |
| 7, | |
| 54, | |
| 55, | |
| 161, | |
| 131, | |
| 184, | |
| 51, | |
| 170, | |
| 12, | |
| 120, | |
| 113, | |
| 95, | |
| 126, | |
| 51, | |
| 98, | |
| 36, | |
| 135, | |
| 54, | |
| 82, | |
| 45, | |
| 95, | |
| 89, | |
| 59, | |
| 95, | |
| 124, | |
| 9, | |
| 113, | |
| 58, | |
| 85, | |
| 51, | |
| 134, | |
| 121, | |
| 169, | |
| 105, | |
| 21, | |
| 30, | |
| 11, | |
| 50, | |
| 65, | |
| 12, | |
| 43, | |
| 82, | |
| 145, | |
| 152, | |
| 97, | |
| 106, | |
| 55, | |
| 31, | |
| 85, | |
| 38, | |
| 112, | |
| 102, | |
| 168, | |
| 123, | |
| 97, | |
| 21, | |
| 83, | |
| 158, | |
| 26, | |
| 80, | |
| 63, | |
| 5, | |
| 81, | |
| 32, | |
| 11, | |
| 28, | |
| 148 | |
| ], | |
| "learning_rate": 0.75, | |
| "gamma": 0.95, | |
| "max_epsilon": 1.0, | |
| "min_epsilon": 0.05, | |
| "decay_rate": 0.005 | |
| } |