A policy maps a robot’s observations or environmental states to actions, specifying how an agent behaves. section 5.2
In reinforcement learning, an agent interacts with an environment, receives rewards, and learns a policy that captures behavior associated with high rewards. section 5.2
Simulation-to-real control
Train a policy in simulation, then use it to control a real robot in target scenarios; adapt it with real-robot training when necessary. section 5.2




















