Commit graph

1033 commits

Author SHA1 Message Date
mmaheshwari2
0494514f4e fixed merge 2025-03-02 12:53:09 -08:00
Isadora White
37b1fc0bed increase timeout length for adding bot to world for the first time 2025-03-01 21:37:20 -08:00
Isadora White
af79c78fbb fixing evaluation script to actually add bots as op and add new models 2025-03-01 19:21:35 -08:00
Isadora White
a42c782b0b better tasks and better few shot prompts for collaboration 2025-03-01 15:47:38 -08:00
Isadora White
ae39028d3b longer sleeps, early breaking for scenarios where there is only one agent 2025-02-28 18:31:19 -08:00
Isadora White
39cec7cf82 changed the checking if complete cycle to be more frequent and updated the collab_profile 2025-02-28 16:59:56 -08:00
mmaheshwari2
23bf693fc2 debugging merge 2025-02-28 16:31:06 -08:00
mmaheshwari2
4d2e2c9b31 debugging merge 2025-02-28 16:29:37 -08:00
Isadora White
2bd6b2cb49 log this.task_id in task.js 2025-02-28 14:42:00 -08:00
Ayushmaniar
42c8062bcf
Merge pull request #3 from icwhite/cooking_tasks
Cooking tasks - Internal Merge
2025-02-28 13:29:55 -08:00
Isadora White
8c2bd816b7 merge conflicts resolved 2025-02-27 21:00:41 -08:00
mmaheshwari2
78ce03fde7 added todo for tools for agents in inventory 2025-02-27 16:24:26 -08:00
Ayush Maniar
fd4f952a2c Added example tasks for different goals per agent 2025-02-25 22:47:43 -08:00
mmaheshwari2
872ca99f08 added ladder fix to inventory 2025-02-25 15:53:53 -08:00
mmaheshwari2
ff5882db30 fixed door inventory 2025-02-25 15:39:26 -08:00
Isadora White
332ad0a0e2 getting rid of unnecessary changes 2025-02-23 21:17:27 -08:00
Isadora White
7cafc254d1 making the default to load in the collaborative profiles 2025-02-23 21:11:08 -08:00
Isadora White
f4125a05d3 add tasks files 2025-02-23 20:43:33 -08:00
Isadora White
2da97b5607 adding a mechanism to add environment variables to the keys.json automatically 2025-02-23 18:55:13 -08:00
Isadora White
1e581a9981 deleting unnecessary files 2025-02-23 17:53:53 -08:00
Isadora White
0a597b5353 making multi agent few shot prompting 2025-02-23 17:50:02 -08:00
Ayush Maniar
57c47c0bcf Provide agent specific goals in task, added more example tasks 2025-02-23 03:21:59 -08:00
Ayush Maniar
0c237b76da Merge branch 'cooking_tasks' of https://github.com/icwhite/mindcraft into cooking_tasks 2025-02-23 02:59:46 -08:00
Ayush Maniar
786bee36d3 Added different initialization for cooking_tasks 2025-02-23 02:53:45 -08:00
Ayush Maniar
1ba5f130f3 Improve task.js with better modularized code 2025-02-23 02:50:11 -08:00
Ayush Maniar
2f8248955e Add some example cooking tasks 2025-02-23 02:41:51 -08:00
Isadora White
8a75d8a78e changing the give to player command to account for an edge case where the players are too close together and moving away takes time 2025-02-22 17:53:42 -08:00
Isadora White
719b72da9e set up to use s3 logging instead of wandb 2025-02-21 17:02:21 -08:00
Max Robinson
5f8ac361b0
Merge pull request #458 from icwhite/clean_dev
Small Fixes
2025-02-21 10:13:22 -06:00
Isadora White
d4565aa68c small fixes, the items were being given twice to the agents on initialization and accounting for blocked_actions not being in the task file 2025-02-20 21:45:29 -08:00
Max Robinson
d5fde29a7b
Merge pull request #452 from icwhite/evaluation_parallelization
Evaluation parallelization
2025-02-20 19:58:15 -06:00
Max Robinson
9364753c29
Merge pull request #457 from kolbytn/fix_pause_selfprompt
Fix pause selfprompt
2025-02-20 19:54:03 -06:00
MaxRobinsonTheGreat
31bce024a2 fixed shouldInterrupt, added test task 2025-02-20 18:17:06 -06:00
MaxRobinsonTheGreat
b23f4776b1 add state to self prompter for pausing 2025-02-20 17:17:21 -06:00
mmaheshwari2
41939450b8 reduced construction task examples size. variants are now variable for construction tasks 2025-02-19 18:34:12 -08:00
mmaheshwari2
2cdafc70a4 new construciton tasks with dynamic timeouts 2025-02-19 18:27:01 -08:00
mmaheshwari2
baaab58f98 3 big changes. 1:blueprint removed from blueprint.explain() 2:construction validation no longer includes air particles 3:autodeletes blueprint before construction task. 2025-02-19 18:25:59 -08:00
Copper
bad2cab931
Why have 'tools' if it's just null? 2025-02-19 17:26:45 -08:00
Copper
55d595121c
Acknowledge and apply requested changes 2025-02-19 17:24:18 -08:00
Isadora White
7a19f34e22
Merge branch 'main' into evaluation_parallelization 2025-02-18 18:34:46 -08:00
Isadora White
bf0bd83cae removing unnecessary files 2025-02-18 16:46:15 -08:00
Isadora White
aad19d616c fixed evaluation script to allow for parallel worlds again 2025-02-18 16:39:31 -08:00
MaxRobinsonTheGreat
7d9257036c log error message/stack 2025-02-18 00:15:34 -06:00
Isadora White
fb5d95debe fixed the issue with garbling commands by instead putting the commands in a bash script and running them that way 2025-02-17 17:25:12 -08:00
Copper
b4f5b5bed6
Merge branch 'kolbytn:main' into main 2025-02-17 15:56:11 -08:00
FateUnix29
600df8e475 Groq updates 2025-02-17 15:49:52 -08:00
MaxRobinsonTheGreat
821dbae5c3 dont default to ollama 2025-02-17 17:34:55 -06:00
MaxRobinsonTheGreat
7a9faca7c3 catch broken embedding models 2025-02-17 16:55:36 -06:00
MaxRobinsonTheGreat
f8278c8a46 add error to groq 2025-02-17 16:47:45 -06:00
MaxRobinsonTheGreat
b1a36b15c2 added more logging 2025-02-17 16:37:54 -06:00