ViperEkura
754624acf0
feat: add online rollout framework for RL strategies
- RolloutRunner: generate + score responses with cached re-rollout trigger
- BaseStrategy.__call__ switches online/offline via runner injection
- GRPO/DPO implement prepare_from_rollout; aliases online_grpo/online_dpo
- TrainConfig + train.py add rollout params and CLI flags
- Tests cover generate_responses, RolloutRunner cache, shared __call__
2026-07-20 03:49:56 +08:00
..
2026-07-19 14:49:58 +08:00
2026-07-19 12:27:56 +08:00
2026-07-20 03:49:56 +08:00
2026-05-18 14:24:00 +08:00
2026-04-05 22:40:16 +08:00