liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
323 lines
7.6 KiB
JSON
323 lines
7.6 KiB
JSON
{
|
|
"artifacts": [
|
|
{
|
|
"kind": "metrics",
|
|
"path": "metrics.json",
|
|
"sha256": "e77f6a79ddf199c92eca1642883921cbd0fb8a2988763a2b1ef604a7e4dc0a91"
|
|
},
|
|
{
|
|
"kind": "events",
|
|
"path": "predictive_episode_events.json",
|
|
"sha256": "9fcb00648c516a3766e13e535fce41522f5d49881221c551e1675a22c7225421"
|
|
},
|
|
{
|
|
"kind": "scene",
|
|
"path": "scene_initial.png",
|
|
"sha256": "8afa759bc85408f14d75d03da1ad57e32dc6824879f3f9911374b0f866e369e5"
|
|
}
|
|
],
|
|
"blockers": [],
|
|
"experiment_id": "6-12",
|
|
"kind": "desktop_manipulation_planning",
|
|
"metrics": {
|
|
"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
|
|
},
|
|
"schema_version": "3.0",
|
|
"seed": 20260808,
|
|
"status": "complete",
|
|
"tool_contract": [
|
|
"observe_scene",
|
|
"pick",
|
|
"place",
|
|
"verify_state",
|
|
"stop"
|
|
],
|
|
"xlerobot_robocrew_extension": {
|
|
"actuation_attempted": false,
|
|
"status": "gated",
|
|
"tool_adapter_required": true
|
|
}
|
|
}
|