Commit History

refactor: Update task configurations and grading logic for improved scoring and consistency
dccaaac

ajaxwin commited on

refactor: Reward clamping in graders
41a051f

ajaxwin commited on

refactor: Task3 reward model changed, agent adjusted for new model
48661cd

ajaxwin commited on

refactor: Improved grading logic for task 2
f78cba2

ajaxwin commited on

refactor: grader trivial bug,
7f7bcc6

ajaxwin commited on

refactor: Update ActionType to include costs and modified grader for task 1
5235476

ajaxwin commited on

refactor: Rename submit_function to submit and removes asserts from eval.py
277ec6e

ajaxwin commited on

refactor: Update grading logic and submission handling across tasks for improved accuracy and consistency
cfae7a7

ajaxwin commited on

fix: Handle optional request body in reset endpoint and set default task ID
a503619

ajaxwin commited on

fix: Update API responses to return JSON format and remove deprecated file references
cfd3cfa

ajaxwin commited on

fix: update file path for landing page in root endpoint
7940abd

ajaxwin commited on

html file path and api corrected
c27e659

ajaxwin commited on

fix: Update file paths and ensure model loading in PropertyRetriever
45bd962

ajaxwin commited on

feat: Add landing page and API documentation
17ed3a7

ajaxwin commited on

fix import paths in app.py to reflect correct module structure
0304fd3

ajaxwin commited on

Structure Changed, files reviewed
88875f7

ajaxwin commited on