{ "geometry": { "P": [ [ 25.964965014274643, 7.907481098825008 ], [ 7.907481098825008, 3.7253031720367233 ] ], "K": [ [ 7.41834055894744, 3.692685860475955 ] ], "Acl": [ [ 1.1, 0.1 ], [ -0.741834055894744, 0.5807314139524045 ] ], "alpha_P": 0.34186659777540374 }, "corollary_scale_without_hidden_constant": 540.8960321628343, "scaling_check": { "reference_action": -0.7879881985533931, "rows": [ [ 16, 0.40288271194521225 ], [ 32, 0.2947227871130451 ], [ 64, 0.2866201034024134 ], [ 128, 0.1812154792030078 ], [ 256, 0.13911474102283775 ] ], "loglog_slope": -0.3769821614173196 }, "episodes": { "lqr": { "mean_cost": 123.0477797801287, "std_cost": 18.24211340891787, "escape_rate": 0.0, "fallback_rate_per_step": 0.0, "mean_rollout_samples_per_step": 0.0, "mean_action_se": 0.0 }, "residual": { "mean_cost": 123.12291688874731, "std_cost": 18.250637612881796, "escape_rate": 0.0, "fallback_rate_per_step": 0.0, "mean_rollout_samples_per_step": 0.0, "mean_action_se": 0.0 }, "fixed": { "mean_cost": 121.97319189256291, "std_cost": 20.423515108573838, "escape_rate": 0.0, "fallback_rate_per_step": 0.0, "mean_rollout_samples_per_step": 64.0, "mean_action_se": 0.09421580586643152 }, "budgeted": { "mean_cost": 122.91527165156262, "std_cost": 15.888757745158458, "escape_rate": 0.0, "fallback_rate_per_step": 0.0685, "mean_rollout_samples_per_step": 32.156, "mean_action_se": 0.12249423455673673 } }, "temperature_sweep": { "fixed0.15": { "cost": 126.83604881105603, "escape": 0.0, "samples": 64.0 }, "budgeted0.15": { "cost": 124.35787485732214, "escape": 0.0, "samples": 35.9488 }, "fixed0.35": { "cost": 126.59043619641565, "escape": 0.0, "samples": 64.0 }, "budgeted0.35": { "cost": 124.31547881774884, "escape": 0.0, "samples": 32.3264 }, "fixed0.7": { "cost": 126.18047959034759, "escape": 0.0, "samples": 64.0 }, "budgeted0.7": { "cost": 123.93862293744692, "escape": 0.0, "samples": 28.985599999999998 } } }