Reinforcement learning is a machine learning training strategy that rewards desirable behaviours while penalising undesirable ones. A reinforcement learning agent can perceive and comprehend its surroundings, act, and learn through trial and error in general.
Trajectory optimization, motion planning, dynamic pathing, controller optimization, and scenario-based learning policies for highways are some of the autonomous driving activities where reinforcement learning could be used. Learning automated parking policies, for example, can help with parking.