Maximum Entropy Inverse Reinforcement Learning

Maximum Entropy Inverse Reinforcement LearningBrianD. Ziebart, Andrew Maas, Bagnell,andAnind K. DeySchool of Computer ScienceCarnegie Mellon UniversityPittsburgh, PA research has shown the benefit of framing problemsof imitation Learning as solutions to Markov Decision Prob-lems. This approach reduces Learning to the problem of re-covering a utility function that makes the behavior inducedby a near-optimal policy closely mimic demonstrated behav-ior. In this work, we develop a probabilistic approach basedon the principle of Maximum Entropy . Our approach providesa well-defined, globally normalized distribution over decisionsequences, while providing the same performance guaranteesas existing develop our technique in the context of modeling real-world navigation and driving behaviors where collected datais inherently noisy and imperfect.

Introduction In problems of imitation learning the goal is to learn to pre-dictthebehavior anddecisionsanagentwouldchoose–e.g., the motions a person would take to grasp an object or the ... Maximum Entropy Inverse Reinforcement Learning ...

Tags:

  Introduction, Learning, Maximum, Reinforcement, Inverse, Entropy, Maximum entropy inverse reinforcement learning

Information

Related search queries