atropos/atroposlib/envs/reward_fns
2025-05-27 13:29:45 +10:00
..
__init__.py first commit 2025-04-29 12:10:10 -07:00
accuracy_reward.py first commit 2025-04-29 12:10:10 -07:00
cascading_r1_math_reward.py first commit 2025-04-29 12:10:10 -07:00
chandas_meter_reward.py Integrate Sanskrit Poetry Environment from KhoomeiK - Add ChandasMeterReward to reward function registry - Move sanskrit_poetry_env.py to environments/community/sanskrit_poetry/ - Add comprehensive documentation as entry #25 in community README - Environment supports traditional Sanskrit meter validation using chandas classifier - Includes IAST to SLP1 transliteration for accurate meter analysis - Fixed code formatting with pre-commit hooks 2025-05-27 13:29:45 +10:00
combined_reward.py first commit 2025-04-29 12:10:10 -07:00
cosine_scaled_reward.py Remove dependency on torch for default installation 2025-05-12 10:17:41 -05:00
crossword_format_reward.py first commit 2025-04-29 12:10:10 -07:00
format_reward.py first commit 2025-04-29 12:10:10 -07:00
r1_reward.py first commit 2025-04-29 12:10:10 -07:00
reasoning_steps_reward.py first commit 2025-04-29 12:10:10 -07:00
registry.py first commit 2025-04-29 12:10:10 -07:00
repetition_penalty_reward.py first commit 2025-04-29 12:10:10 -07:00
reward_function.py first commit 2025-04-29 12:10:10 -07:00