{ "cells": [ { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 0, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 6.0, "mode": "closed_loop", "recoveries": 0, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 6.0, "mode": "predictive", "recoveries": 0, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 34, "seed": 20260808, "success_rate": 0.734375 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 6.53125, "mode": "closed_loop", "recoveries": 34, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 6.53125, "mode": "predictive", "recoveries": 34, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 60, "seed": 20260808, "success_rate": 0.53125 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 6.9375, "mode": "closed_loop", "recoveries": 60, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 6.9375, "mode": "predictive", "recoveries": 60, "seed": 20260808, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 0, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 6.0, "mode": "closed_loop", "recoveries": 0, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 6.0, "mode": "predictive", "recoveries": 0, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 34, "seed": 20260809, "success_rate": 0.734375 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 6.53125, "mode": "closed_loop", "recoveries": 34, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 6.53125, "mode": "predictive", "recoveries": 34, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 60, "seed": 20260809, "success_rate": 0.53125 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 6.9375, "mode": "closed_loop", "recoveries": 60, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 6.9375, "mode": "predictive", "recoveries": 60, "seed": 20260809, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 0, "seed": 20260810, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 6.0, "mode": "closed_loop", "recoveries": 0, "seed": 20260810, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.0, "mean_tool_calls": 6.0, "mode": "predictive", "recoveries": 0, "seed": 20260810, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 33, "seed": 20260810, "success_rate": 0.7421875 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 6.515625, "mode": "closed_loop", "recoveries": 33, "seed": 20260810, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.25, "mean_tool_calls": 6.515625, "mode": "predictive", "recoveries": 33, "seed": 20260810, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 4.0, "mode": "open_loop", "recoveries": 59, "seed": 20260810, "success_rate": 0.5390625 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 6.921875, "mode": "closed_loop", "recoveries": 59, "seed": 20260810, "success_rate": 1.0 }, { "episodes": 128, "failure_probability": 0.5, "mean_tool_calls": 6.921875, "mode": "predictive", "recoveries": 59, "seed": 20260810, "success_rate": 1.0 } ], "deterministic_replay": true, "device": { "device": "mps", "name": "Apple Metal Performance Shaders", "torch": "2.7.0" }, "models": [ { "seed": 20260808, "test_mse": 0.017016880214214325, "train_mse": 0.017159195616841316 }, { "seed": 20260809, "test_mse": 0.012364446185529232, "train_mse": 0.01264232862740755 }, { "seed": 20260810, "test_mse": 0.014977166429162025, "train_mse": 0.015084807761013508 } ], "protocol": { "episodes_per_cell": 128, "failure_probabilities": [ 0.0, 0.25, 0.5 ], "seeds": [ 20260808, 20260809, 20260810 ], "total_episodes": 3456 }, "wall_time_ms": 8197.975 }