lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

run operagor

Browse Source
This commit is contained in:
yuanmengqi
2025-07-14 07:13:17 +00:00
parent b8b026f817
commit 5d90faa548
6 changed files with 16 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
evaluation_examples/examples/chrome/9f935cce-0a9f-435f-8007-817732bfc0a5.json
View File

@@ -57,5 +57,5 @@
} }
} }
}, },
"proxy": true "proxy": false
} }

2
evaluation_examples/examples/chrome/a728a36e-8bf1-4bb6-9a03-ef039a5233f0.json
View File

@@ -56,5 +56,5 @@
} }
} }
}, },
"proxy": true "proxy": false
} }

4
evaluation_examples/settings/proxy/dataimpulse.json
View File

@@ -2,8 +2,8 @@
{ {
"host": "gw.dataimpulse.com", "host": "gw.dataimpulse.com",
"port": 823, "port": 823,
"username": "your_username", "username": "e750e5abb74376d28361",
"password": "your_password", "password": "e5ec245537e1e76a",
"protocol": "http", "protocol": "http",
"provider": "dataimpulse", "provider": "dataimpulse",
"type": "residential", "type": "residential",

4
monitor/.env
View File

@@ -4,11 +4,11 @@
# Monitor configuration # Monitor configuration
TASK_CONFIG_PATH=../evaluation_examples/test_all.json TASK_CONFIG_PATH=../evaluation_examples/test_all.json
EXAMPLES_BASE_PATH=../evaluation_examples/examples EXAMPLES_BASE_PATH=../evaluation_examples/examples
RESULTS_BASE_PATH=../results_all RESULTS_BASE_PATH=../results_operator_full_test_0713
ACTION_SPACE=pyautogui ACTION_SPACE=pyautogui
OBSERVATION_TYPE=screenshot OBSERVATION_TYPE=screenshot
MODEL_NAME=computer-use-preview MODEL_NAME=computer-use-preview
MAX_STEPS=150 MAX_STEPS=100
FLASK_PORT=80 FLASK_PORT=80
FLASK_HOST=0.0.0.0 FLASK_HOST=0.0.0.0
FLASK_DEBUG=true FLASK_DEBUG=true

9
run_operator.sh Normal file
View File

@@ -0,0 +1,9 @@
python run_multienv_openaicua.py \
--headless \
--observation_type screenshot \
--model computer-use-preview \
--result_dir ./results_operator_full_test_0713 \
--test_all_meta_path evaluation_examples/test_all.json \
--max_steps 100 \
--num_envs 15 \
--provider_name aws

2
show_result.py
View File

@@ -68,4 +68,4 @@ def get_result(action_space, use_model, observation_type, result_dir):
if __name__ == '__main__': if __name__ == '__main__':
get_result("pyautogui", "gpt-4o", "a11y_tree", "./results") get_result("pyautogui", "computer-use-preview", "screenshot", "./results_operator_full_test_0713")