On-policy RL is a form of reinforcement learning that updates a policy using actions and outcomes generated under that same policy. Used in AI model training, it differs from off-policy RL, which can also learn from data collected under older or different policies.
on-policy RL
On-policy RL is a reinforcement-learning approach that updates a policy using experience generated by that same policy.
2 articlesLast mentioned
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.
Articles covering this entry
AI Agent Tuning: When to Rewrite Prompts and When to Retrain WeightsAI Performance ·
If the teacher's weights are open, consider on-policy distillation before pure RL.
Read articlePre-Training, Fine-Tuning and RL: Where Frontier LLMs Get Their QualityAI Performance ·
A key property of GRPO is that it is on-policy: the model trains only on traces it generated itself.
Read article