PDF Publication Title:
Text from PDF Page: 009
1 Reinforcement learning (RL) is the branch of machine learn- ing that is concerned with making sequences of decisions. It considers an agent situated in an environment: each timestep, the agent takes an action, and it receives an obser- vation and reward. An RL algorithm seeks to maximize the agent’s total reward, given a previously unknown environ- ment, through a trial-and-error learning process. Chapter 2 provides a more detailed description of the mathematical formulation of reinforcement learning. The reinforcement learning problem sketched above, involving a reward-maximizing agent, is extremely general, and RL algorithms have been applied in a variety of differ- ent fields, from business inventory management [VR+97] to robot control [KBP13], to structured prediction [DILM09] 1.2 deep learning Modern machine learning is mostly concerned with learning functions from data. Deep learning is based on a simple recipe: choose a loss function, choose an expressive func- tion approximator (a deep neural network), and optimize the parameters with gradient descent. The remarkable empirical finding is that it is possible to learn functions that perform complicated multi-step computations with this recipe, as has been shown by groundbreaking results in object recognition [KSH12] and speech recognition [Dah+12]. The recipe involves a reduction from a learning problem to an optimization problem: in supervised learning, we are reducing obtain a function that makes good predictions on unseen 1 INTRODUCTION 1.1 reinforcement learning action Agent observation, reward EnvironmentPDF Image | OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHS
PDF Search Title:
OPTIMIZING EXPECTATIONS: FROM DEEP REINFORCEMENT LEARNING TO STOCHASTIC COMPUTATION GRAPHSOriginal File Name Searched:
thesis-optimizing-deep-learning.pdfDIY PDF Search: Google It | Yahoo | Bing
Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info
Cruising Review Topics and Articles More Info
Software based on Filemaker for the travel industry More Info
The Burgenstock Resort: Reviews on CruisingReview website... More Info
Resort Reviews: World Class resorts... More Info
The Riffelalp Resort: Reviews on CruisingReview website... More Info
CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com (Standard Web Page)