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
372 lines
8.8 KiB
JSON
372 lines
8.8 KiB
JSON
{
|
|
"aggregate_success_rate": 1.0,
|
|
"cells": [
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.2301437109708786,
|
|
"mean_steps": 12.97265625,
|
|
"objects_per_episode": 1,
|
|
"p95_steps": 20.0,
|
|
"seed": 20260808,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.5379001498222351,
|
|
"mean_steps": 30.263671875,
|
|
"objects_per_episode": 2,
|
|
"p95_steps": 48.0,
|
|
"seed": 20260808,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.8478867411613464,
|
|
"mean_steps": 47.666015625,
|
|
"objects_per_episode": 3,
|
|
"p95_steps": 71.0,
|
|
"seed": 20260808,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 1.1540141105651855,
|
|
"mean_steps": 64.80859375,
|
|
"objects_per_episode": 4,
|
|
"p95_steps": 94.0,
|
|
"seed": 20260808,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.23004719614982605,
|
|
"mean_steps": 12.966796875,
|
|
"objects_per_episode": 1,
|
|
"p95_steps": 20.0,
|
|
"seed": 20260809,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.5500189065933228,
|
|
"mean_steps": 30.943359375,
|
|
"objects_per_episode": 2,
|
|
"p95_steps": 49.0,
|
|
"seed": 20260809,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.8587707281112671,
|
|
"mean_steps": 48.28515625,
|
|
"objects_per_episode": 3,
|
|
"p95_steps": 72.0,
|
|
"seed": 20260809,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 1.1936140060424805,
|
|
"mean_steps": 67.0859375,
|
|
"objects_per_episode": 4,
|
|
"p95_steps": 97.0,
|
|
"seed": 20260809,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.2288360595703125,
|
|
"mean_steps": 12.904296875,
|
|
"objects_per_episode": 1,
|
|
"p95_steps": 20.0,
|
|
"seed": 20260810,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.5454419851303101,
|
|
"mean_steps": 30.68359375,
|
|
"objects_per_episode": 2,
|
|
"p95_steps": 49.0,
|
|
"seed": 20260810,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.8452757596969604,
|
|
"mean_steps": 47.515625,
|
|
"objects_per_episode": 3,
|
|
"p95_steps": 72.0,
|
|
"seed": 20260810,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 1.1632212400436401,
|
|
"mean_steps": 65.373046875,
|
|
"objects_per_episode": 4,
|
|
"p95_steps": 95.44998168945312,
|
|
"seed": 20260810,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.2274591028690338,
|
|
"mean_steps": 12.8359375,
|
|
"objects_per_episode": 1,
|
|
"p95_steps": 20.0,
|
|
"seed": 20260811,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.5360898971557617,
|
|
"mean_steps": 30.140625,
|
|
"objects_per_episode": 2,
|
|
"p95_steps": 49.0,
|
|
"seed": 20260811,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.8582804799079895,
|
|
"mean_steps": 48.23828125,
|
|
"objects_per_episode": 3,
|
|
"p95_steps": 71.0,
|
|
"seed": 20260811,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 1.1563987731933594,
|
|
"mean_steps": 64.9453125,
|
|
"objects_per_episode": 4,
|
|
"p95_steps": 93.0,
|
|
"seed": 20260811,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.22869494557380676,
|
|
"mean_steps": 12.8984375,
|
|
"objects_per_episode": 1,
|
|
"p95_steps": 20.0,
|
|
"seed": 20260812,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.5435010194778442,
|
|
"mean_steps": 30.57421875,
|
|
"objects_per_episode": 2,
|
|
"p95_steps": 49.0,
|
|
"seed": 20260812,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 0.8587590456008911,
|
|
"mean_steps": 48.322265625,
|
|
"objects_per_episode": 3,
|
|
"p95_steps": 74.0,
|
|
"seed": 20260812,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
},
|
|
{
|
|
"control_hz": 20,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"episodes": 512,
|
|
"max_steps": 900,
|
|
"mean_path_length_m": 1.1580641269683838,
|
|
"mean_steps": 65.076171875,
|
|
"objects_per_episode": 4,
|
|
"p95_steps": 94.0,
|
|
"seed": 20260812,
|
|
"success_rate": 1.0,
|
|
"successes": 512
|
|
}
|
|
],
|
|
"deterministic_replay": true,
|
|
"device": {
|
|
"device": "mps",
|
|
"name": "Apple Metal Performance Shaders",
|
|
"torch": "2.7.0"
|
|
},
|
|
"max_p95_steps": 97.0,
|
|
"protocol": {
|
|
"episodes_per_cell": 512,
|
|
"object_counts": [
|
|
1,
|
|
2,
|
|
3,
|
|
4
|
|
],
|
|
"seeds": [
|
|
20260808,
|
|
20260809,
|
|
20260810,
|
|
20260811,
|
|
20260812
|
|
],
|
|
"total_episodes": 10240
|
|
},
|
|
"wall_time_ms": 2806.997,
|
|
"worst_cell_success_rate": 1.0
|
|
}
|