Please use this identifier to cite or link to this item:
http://arks.princeton.edu/ark:/88435/dsp01j67316994
Title: | Learning Algorithms for Intelligent Agents and Mechanisms |
Authors: | Rahme, Jad |
Advisors: | Adams, Ryan P |
Contributors: | Applied and Computational Mathematics Department |
Keywords: | Bayesian Statistics Deep Learning Game Theory Mechanism Design Reinforcement Learning Statistical Physics |
Subjects: | Artificial intelligence Applied mathematics |
Issue Date: | 2022 |
Publisher: | Princeton, NJ : Princeton University |
Abstract: | The ability to learn from past experiences and adapt one’s behavior accordingly within an environment or context to achieve a certain goal is a characteristic of a truly intelligent entity. Developing efficient, robust, and reliable learning algorithms towards that end is an active area of research and a major step towards achieving artificial general intelligence. In this thesis, we research learning algorithms for optimal decision making in two different contexts, Reinforcement Learning in Part I and Auction Design in Part II. Reinforcement learning (RL) is an area of machine learning that is concerned with how an agent should act in an environment in order to maximize its cumulative reward over time. In Chapter 2, inspired by statistical physics, we develop a novel approach to RL that not only learns optimal policies with enhanced desirable properties but also sheds new light on maximum entropy RL. In Chapter 3, we tackle the generalization problem in RL using a Bayesian perspective. We show that imperfect knowledge of the environment’s dynamics effectively turn a fully-observed Markov Decision Process (MDP) into a Partially Observed MDP (POMDP) that we call the Epistemic POMDP. Informed by this observation, we develop a new policy learning algorithm LEEP which has improved generalization properties. An auction is the process of organizing the buying and selling of products and services that is of great practical importance. Designing an incentive compatible, individually rational auction that maximizes revenue is a challenging and intractable problem. Recently, a deep learning based approach was proposed to learn optimal auctions from data. While successful, this approach suffers from a few limitations, including sample inefficiency, lack of generalization to new auctions, and training difficulties. In Chapter 4, we construct a symmetry preserving neural network architecture, EquivariantNet, suitable for anonymous auctions. EquivariantNet is not only more sample efficient but is also able to learn auction rules that generalize well to other settings. In Chapter 5, we propose a novel formulation of the auction learning problem as a two player game. The resulting learning algorithm, ALGNet, is easier to train, more reliable and better suited for non stationary settings. |
URI: | http://arks.princeton.edu/ark:/88435/dsp01j67316994 |
Alternate format: | The Mudd Manuscript Library retains one bound copy of each dissertation. Search for these copies in the library's main catalog: catalog.princeton.edu |
Type of Material: | Academic dissertations (Ph.D.) |
Language: | en |
Appears in Collections: | Applied and Computational Mathematics |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Rahme_princeton_0181D_14181.pdf | 5.12 MB | Adobe PDF | View/Download |
Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.