| { | |
| "learning_rate": 0.001, | |
| "ent_coef": 0.0, | |
| "max_grad_norm": 0.5, | |
| "clip_range": 0.2, | |
| "vf_coef": 0.5, | |
| "description": "Modify any hyperparameter in this file. Changes are applied at the start of the next epoch.", | |
| "supported_params": [ | |
| "learning_rate - Learning rate for optimizer", | |
| "ent_coef - Entropy coefficient", | |
| "max_grad_norm - Maximum gradient norm for clipping", | |
| "clip_range - PPO clipping range (PPO only)", | |
| "vf_coef - Value function coefficient (PPO only)" | |
| ], | |
| "last_modified": 1755381605.2407584 | |
| } |