[CS391R] Overview of Robot Decision Making

• Robot Decision making: Choosing the actions a robot performs in the physical world
• Mathematical Framework of Sequential Decision Making
  • Markov Decision Process
• Learning for Decision Making
  1. reinforcement learning (model-free vs. model-based, online vs offline)
     • Optimizes the policy by trial and error in an MDP.
     • Goal: To maximize the long-term rewards
  2. imitation learning (behavior cloning, DAgger, IRL, and adversarial learning)
     • Optimizes policy by imitating the expert in an MDP
     • Goal: To match the behavioral distributions
     • Types
       • Direct estimation of the expert policy from expert data (behavioral cloning, supervised learning version)
       • Reconstruct a reward function (inverse RL) and then learn a policy from the reward (RL)