glossary_term · Angestrom

RLHF

Reinforcement learning from human feedback — tuning a model toward preferred answers.

Reinforcement learning from human feedback — tuning a model toward preferred answers. Reinforcement learning from human feedback — tuning a model toward preferred answers.

Read it here, in full.View original →

paperReinforcement Learning without Ground-Truth Solutions can Improve LLMs paperJoint Learning of Experiential Rules and Policies for Large Language Model Agents paperAutomating Potential-based Reward Shaping with Vision Language Model Guidance

paperAutomating Potential-based Reward Shaping with Vision Language Model Guidance paperJoint Learning of Experiential Rules and Policies for Large Language Model Agents paperReinforcement Learning without Ground-Truth Solutions can Improve LLMs

rl alignment