Reinforcement Learning Intermediate
reward
In reinforcement learning, the numerical result of taking an action in a state, as defined by the environment.
Plain English Explanation
In reinforcement learning, the numerical result of taking an action in a state, as defined by the environment.
How is it used?
Practitioners refer to reward when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.