Custom rollout and reward functions via LLM.reinforcement_step() and ReinforcementStep

You can now develop your own custom rollout and reward functionality while using Fireworks to manage the training and deployment of your models. This gives you full control over your reinforcement learning workflows while leveraging Fireworks' infrastructure for model training and deployment.

See the new LLM.reinforcement_step() method and ReinforcementStep class for usage examples and details.