| { | |
| "policy": "best-of-N over periodic checkpoints", | |
| "selected": { | |
| "gradient_step": 40000 | |
| }, | |
| "selection_metric": null, | |
| "candidates": { | |
| "unit": "gradient_steps", | |
| "every": 10000, | |
| "configured_budget": 60000 | |
| }, | |
| "eval_protocol": { | |
| "episodes_per_env": 50, | |
| "weights": "ema", | |
| "id_envs": [ | |
| "MiniHack-Room-Random-5x5-v0", | |
| "MiniHack-Room-Random-15x15-v0", | |
| "MiniHack-Corridor-R2-v0", | |
| "MiniHack-MazeWalk-9x9-v0" | |
| ], | |
| "ood_envs": [ | |
| "MiniHack-Room-Dark-15x15-v0", | |
| "MiniHack-Corridor-R5-v0", | |
| "MiniHack-MazeWalk-45x19-v0" | |
| ] | |
| } | |
| } | |