diff --git a/evaluation_examples/test_0607.json b/evaluation_examples/test_0607.json new file mode 100644 index 0000000..574901b --- /dev/null +++ b/evaluation_examples/test_0607.json @@ -0,0 +1,5 @@ +{ + "vlc": [ + "8d9fd4e2-6fdb-46b0-b9b9-02f06495c62f" + ] +} \ No newline at end of file diff --git a/run_operator_vlc.sh b/run_operator_vlc.sh new file mode 100644 index 0000000..b6c1e89 --- /dev/null +++ b/run_operator_vlc.sh @@ -0,0 +1,9 @@ +python run_multienv_openaicua.py \ + --headless \ + --observation_type screenshot \ + --model computer-use-preview \ + --result_dir ./results_vlc_retest \ + --test_all_meta_path evaluation_examples/test_0607.json \ + --region us-east-1 \ + --max_steps 3 \ + --num_envs 1