Introduction to Reinforcement Learning

← Back to document page

Introduction to Reinforcement LearningCS 294-112: Deep Reinforcement LearningSergey LevineClass 1 milestone in one week! Don t be late! to start forming final project was e-mailed to youToday s of a Markov decision of Reinforcement Learning of a RL overview of RL algorithm types Goals: Understand definitions & notation Understand the underlying Reinforcement Learning objective Get summary of possible algorithmsDefinitions1. run away2. ignore3. petTerminology & notationImages: Bojarskiet al. 16, NVIDIAtrainingdatasupervisedlearningImit ation LearningReward functionsDefinitionsAndrey MarkovDefinitionsAndrey MarkovRichard BellmanDefinitionsAndrey MarkovRichard BellmanDefinitionsThe goal of Reinforcement learningwe ll come back to partially observed laterThe goal of Reinforcement learningwe ll come back to partially observed laterThe goal of Reinforcement learningwe ll come back to partially observed laterFinite horizon case: state-action marginalstate-action marginalInfinite horizon case: stationary distributionstationary distributionstationary = the same before and after transitionInfinite horizon case: stationary distributionstationary distributionstationary = the same before and after transitionExpectations and stochastic systemsinfinite horizon casefinite horizon caseIn RL, we almost always care about expectations+1-1Algo

Introduction to Reinforcement Learning CS 294-112: Deep Reinforcement Learning Sergey Levine. Class Notes 1. Homework 1 milestone in one week! •Dont be late! 2. Remember to start forming final project groups 3. MuJoCo license was e-mailed to you. Today’s Lecture 1. …

  Introduction, Learning, Reinforcement, Reinforcement learning