| { | |
| "params": { | |
| "temperature_scale": 0.4681, | |
| "explore_bonus": 0.578, | |
| "bias_explore_frontier": -0.2202, | |
| "bias_inspect_novelty": 0.5866, | |
| "bias_test_from_distance": 0.1114, | |
| "bias_seek_shelter": -0.2137, | |
| "bias_rest": 0.1194, | |
| "bias_approach_user": 0.1983 | |
| }, | |
| "baseline_objective": { | |
| "J": 1.4016, | |
| "reward": 1.6434, | |
| "penalty": 0.1209, | |
| "viable_frac": 1.0 | |
| }, | |
| "trained_objective": { | |
| "J": 2.4644, | |
| "reward": 2.6138, | |
| "penalty": 0.0747, | |
| "viable_frac": 1.0 | |
| }, | |
| "reward_gain": 0.9704, | |
| "history": [ | |
| { | |
| "iter": 0, | |
| "best_J": 1.74, | |
| "best_reward": 1.934, | |
| "viable_frac": 1.0 | |
| }, | |
| { | |
| "iter": 1, | |
| "best_J": 2.204, | |
| "best_reward": 2.425, | |
| "viable_frac": 1.0 | |
| }, | |
| { | |
| "iter": 2, | |
| "best_J": 2.247, | |
| "best_reward": 2.443, | |
| "viable_frac": 1.0 | |
| }, | |
| { | |
| "iter": 3, | |
| "best_J": 2.461, | |
| "best_reward": 2.649, | |
| "viable_frac": 1.0 | |
| }, | |
| { | |
| "iter": 4, | |
| "best_J": 2.374, | |
| "best_reward": 2.571, | |
| "viable_frac": 1.0 | |
| }, | |
| { | |
| "iter": 5, | |
| "best_J": 2.464, | |
| "best_reward": 2.614, | |
| "viable_frac": 1.0 | |
| } | |
| ], | |
| "config": { | |
| "iters": 6, | |
| "pop": 24, | |
| "seeds": [ | |
| 4, | |
| 5, | |
| 6, | |
| 8, | |
| 13, | |
| 17, | |
| 23 | |
| ], | |
| "steps": 180, | |
| "window": 40, | |
| "lambda": 2.0 | |
| } | |
| } |