fix: changed grader logic so that absolute 1 and 0 are exclusive from the score) cd27210 10doshi12 commited on 3 days ago
fix: surface episode_score in observation dict to bypass metadata exclusion 9b06368 10doshi12 commited on 5 days ago
main logic complete, inference.py running as expected, now fine tuning the reward functions and scoring to make complete sense and also check openenv spec complaince completely eaf3506 10doshi12 commited on 6 days ago
phase2-6 complete main base simulation logic complete, fine tuning and data backed reward function pending 74dfd77 10doshi12 commited on 6 days ago
initial repository structure complete and base models created, openenv validate confirmed project running 18f9970 10doshi12 commited on 6 days ago