Commit Graph

16 Commits

Author SHA1 Message Date
Timothyxxx
f153a4c253 Add 'WAIT', 'FAIL', 'DONE' to the action space; Debug basic prompting-based GPT-4 and Gemini agents; Initialize experiments script; 2024-01-14 23:36:19 +08:00
Timothyxxx
fa84b20ea5 VLC updates, and some infra bugs fix 2024-01-09 09:30:11 +08:00
Timothyxxx
3cbb57f24c Add the GUI set-of-mark object detector data collection script 2024-01-05 11:00:31 +08:00
Hilbert-Johnson
8ac88e9617 pass test case 2024-01-02 01:10:46 +08:00
Hilbert-Johnson
7560f4dc46 update SoM_agent 2023-12-31 19:13:17 +08:00
Hilbert-Johnson
86c6a473e2 add initail SoM_agent 2023-12-28 13:43:44 +08:00
Timothyxxx
30064ff816 Fix conflicts 2023-12-16 21:32:43 +08:00
Timothyxxx
e51ef4b91d Make up 2023-12-02 18:02:45 +08:00
Timothyxxx
9b214b3d23 Action space thoughts 2023-12-02 18:02:06 +08:00
Timothyxxx
992d8f8fce Refactor with pyautogui 2023-12-02 17:52:00 +08:00
Timothyxxx
e52ba2ab13 Fix the width and height of vm, make agent perform more accurate 2023-11-30 12:10:41 +08:00
Timothyxxx
80b148793d Initialize visual components such as SAM for assistance 2023-11-29 20:22:48 +08:00
Timothyxxx
3d0d9d7758 Run through gpt_4v agent pipeline 2023-11-29 20:21:57 +08:00
Timothyxxx
8470264884 Initialize GPT-4v agent, and prompt for current observation space 2023-11-28 00:38:22 +08:00
Timothyxxx
054f545942 Initialize GPT-4v agent, and prompt for current observation space 2023-11-28 00:23:50 +08:00
Timothyxxx
8272e93953 Add DuckTrack as initial annotation tool; Initial multimodal test 2023-11-27 00:34:57 +08:00