Reinforcement learning from human feedback

lastmod 2023-05-02created 2023-05-021 edits

In machine learning, reinforcement learning from human feedback or reinforcement learning from human preferences is a technique that trains a "reward model" directly from human feedback and uses the model as a reward function to optimize an agent's policy through reinforcement learning via an optimization algorithm such as the following. Proximal policy optimization.

See also

• Deep learning

Favorite site

• Reinforcement learning from human feedback - Wikipedia