shaping agent
Shaping Agents via Human Reinforcement
Knox, W. Bradley (University of Texas at Austin)
As computational learning agents move into domains that incur real costs (e.g., autonomous driving or financial investment), it will be necessary to learn good policies without numerous high-cost learning trials. One promising approach to reducing sample complexity of learning a task is knowledge transfer from humans to agents. Ideally, methods of transfer should be accessible to anyone with task knowledge, regardless of that person's expertise in programming and AI. This thesis statement focuses on allowing a human trainer to interactively shape an agent's policy via reinforcement signals.