| { | |
| "model_type": "tiny-lunar-policy", | |
| "n_params": 14, | |
| "obs_dim": 8, | |
| "n_actions": 4, | |
| "weights_param": "sym_theta", | |
| "weights_shape": [14], | |
| "symmetry": "mirror (x, vx, angle, angular_velocity flip; legs swap; action left<->right)", | |
| "env_id": "LunarLander-v3", | |
| "torch_dtype": "float32", | |
| "observation_names": [ | |
| "x", "y", "vx", "vy", "angle", "angular_velocity", | |
| "leg_left_contact", "leg_right_contact" | |
| ], | |
| "action_meanings": [ | |
| "do nothing", | |
| "fire left orientation engine", | |
| "fire main engine", | |
| "fire right orientation engine" | |
| ], | |
| "metrics": { | |
| "protocol": "greedy, 60 seeds x 100 episodes", | |
| "mean_return_canonical": 264.058, | |
| "mean_return_fresh_seeds": 263.831, | |
| "seeds_with_mean_ge_200": "60/60", | |
| "landing_rate": 0.9955, | |
| "crash_rate": 0.0035 | |
| } | |
| } | |