66 commits

Author	SHA1	Message	Date
Isadora White	a52905092d	flower and church blueprint	2025-04-10 14:04:55 -07:00
Isadora White	074cbcf8f8	three agent pyramid	2025-04-09 16:34:11 -07:00
Isadora White	e20a932614	fixed major bug in construction tasks and cool footage	2025-04-08 20:57:19 -07:00
Ayush Maniar	6bc8585c17	Updated timeout for crafting tasks	2025-04-08 12:26:32 -07:00
Ayush Maniar	d154e46085	Removed cooking task files that are no longer needed	2025-04-07 20:39:05 -07:00
Isadora White	64c0f61828	fixing three agent tasks with long timeout	2025-04-07 16:25:35 -07:00
Isadora White	f2355f16be	adding long timeout tasks for llama evaluation	2025-04-07 15:42:26 -07:00
Isadora White	11db49ce78	make a blueprint for the pyramid tasks	2025-04-04 13:49:12 -07:00
Isadora White	83057cb255	final adjustment	2025-04-03 22:57:27 -07:00
Isadora White	3b80afe813	update to include the better coordinates	2025-04-03 22:55:30 -07:00
Isadora White	3834406f6a	custom task file for small church	2025-04-03 22:44:19 -07:00
Ayush Maniar	3ee72c11f3	Hells kitchen tasks pushed	2025-04-02 10:19:23 -07:00
Isadora White	75037f7596	longer timeout test tasks	2025-03-28 14:57:31 -05:00
Ayush Maniar	7afaba99a4	Added 2 agent fully unblocked test tasks for comparing with 3+ agents performance	2025-03-26 23:24:46 -07:00
Ayush Maniar	a5158674dd	Add new test and train tasks for 3+ agent cooking	2025-03-26 20:32:28 -07:00
Isadora White	fab5721b4e	cooking tasks longer timeout	2025-03-26 19:59:28 -05:00
hlillemark	38c701a8fb	Merge branch 'main' of https://github.com/icwhite/mindcraft	2025-03-25 21:19:15 -07:00
hlillemark	d68d35e74c	Add filtered tasks for 3, 4, 5 agents	2025-03-25 21:18:49 -07:00
Ayush Maniar	4e0ae4b9b7	Merge branch 'main' of https://github.com/icwhite/mindcraft	2025-03-25 20:04:42 -07:00
Ayush Maniar	607c383dfc	New test and train (easier) tasks for 2+ agent cooking	2025-03-25 20:04:39 -07:00
Isadora White	97e158accd	longer timeout	2025-03-25 22:02:35 -05:00
Isadora White	b965123f74	increase timeout	2025-03-23 11:34:20 -05:00
hlillemark	8f9ed98776	add filtered train tasks	2025-03-23 00:15:52 -07:00
Ayush Maniar	4c5320eddb	Added files for filtering easy test tasks (30) and training tasks (500)	2025-03-22 21:37:50 -07:00
Isadora White	93db8b664c	fixing construction tasks	2025-03-22 17:13:14 -05:00
Isadora White	b72500a0ea	Merge branch 'main' into constructionTaskRevision	2025-03-20 20:45:28 -07:00
MaxRobinsonTheGreat	6dc5c6401a	Merge branch 'main' into cleanup	2025-03-20 16:45:20 -05:00
Mehul Maheshwari	12b327f193	Merge branch 'main' into constructionTaskRevision	2025-03-20 12:26:29 -07:00
Isadora White	7b690775ff	updating thinking model prompt to not give instructions and instead act as if it is in a conversation	2025-03-20 14:06:15 -05:00
Isadora White	4db0f8d3c5	further debugging of reasoning models	2025-03-20 13:21:09 -05:00
Ayush Maniar	44bbde9bad	Modified base cooking tasks and added 3+ agent tasks for cooking	2025-03-19 20:36:27 -07:00
MaxRobinsonTheGreat	a6cb062862	add script to run all tasks in task file	2025-03-19 13:53:50 -05:00
MaxRobinsonTheGreat	96250b3ce5	Merge branch 'main' into cleanup	2025-03-19 13:29:37 -05:00
Mehul Maheshwari	a92eb58ad0	fixed tool based problems with construction tasks (ladders needs blocks behind them, door validation fixed)	2025-03-18 17:02:13 -07:00
Isadora White	0dea3c0720	group project tasks	2025-03-16 22:17:31 -07:00
Isadora White	1ccba3a4b5	new train, test, dev tasks and new analysis files	2025-03-16 17:55:05 -07:00
MaxRobinsonTheGreat	eebd43e8a3	Merge branch 'main' into cleanup	2025-03-15 14:19:01 -05:00
MaxRobinsonTheGreat	2597d32488	move multi agent crafting tasks back	2025-03-15 14:16:03 -05:00
Mehul Maheshwari	83ac17a036	revised construction task generation to be by agent count. modified gitignore to match changes	2025-03-14 15:39:58 -07:00
Ayush Maniar	4269c6fea3	Added hells kitchen tasks, improvements to cooking_tasks world reset, more general goals in tasks.js for cooking task.	2025-03-13 21:26:49 -07:00
Mehul Maheshwari	afe13ffc3e	commenting	2025-03-12 19:46:57 -07:00
Mehul Maheshwari	6de37f2ebf	removed logging in procedural generation function	2025-03-12 19:44:28 -07:00
Mehul Maheshwari	ff60dc6a45	Removed large files from Git tracking	2025-03-12 19:42:59 -07:00
Mehul Maheshwari	d9b1e4805f	ignoring construction task files bc too big. generation now has variable number of agents and splits inventory evenly	2025-03-12 19:40:46 -07:00
MaxRobinsonTheGreat	7225699bf1	move task json out of root	2025-03-12 14:19:59 -05:00
Isadora White	379047c5bb	add more single agent tasks	2025-03-10 23:22:37 -07:00
Isadora White	7402839cb5	teleport close to building	2025-03-10 23:08:35 -07:00
Isadora White	57a1fa20b5	update debug tasks	2025-03-09 15:48:10 -07:00
Isadora White	0ee122fb4e	longer timeouts	2025-03-09 14:36:53 -07:00
Isadora White	2f80b65d42	fixing small bugs related to single agent support	2025-03-09 13:01:54 -07:00