Search

Spring 2019

Cholodovskis Machado, Marlos

In the reinforcement learning (RL) problem an agent must learn how to act optimally through trial-and-error interactions with a complex, unknown, stochastic environment. The actions taken by the agent influence not just the immediate reward it observes but also the future states and rewards it...

Fall 2024

Sales-Ortiz, Javier C

This thesis studies a virtual power plant (VPP) that trades the bidirectional charging flexibility of privately owned plug-in electric vehicles (EVs) in a real-time electricity market to maximize its profit. The main contribution of this thesis is the development of scalable and efficient...

Spring 2011

Delp, Michael

Off-policy reinforcement learning is useful in many contexts. Maei, Sutton, Szepesvari, and others, have recently introduced a new class of algorithms, the most advanced of which is GQ(lambda), for off-policy reinforcement learning. These algorithms are the first stable methods for general...

Fall 2022

Daliri,Mohammadreza

OpenSpiel is an open-source software system for implementing high-performance software players for many different computer games. Hex is a two-player game of perfect information used in a variety of computer games research projects. The OpenSpiel project has implemented a version of the AlphaZero...

Fall 2022

Miahi, Erfan

In this thesis, we investigate the connection between the properties and the generalization performance of representations learned by deep reinforcement learning algorithms. Much of the earlier work on representation learning for reinforcement learning focused on designing fixed-basis...

Spring 2010

Naddaf, Yavar

This research focuses on developing AI agents that play arbitrary Atari 2600 console games without having any game-specific assumptions or prior knowledge. Two main approaches are considered: reinforcement learning based methods and search based methods. The RL-based methods use feature vectors...

Fall 2022

Lo, Chunlok

This thesis investigates a new approach to model-based reinforcement learning using background planning: mixing (approximate) dynamic programming updates and model-free updates, similar to the Dyna architecture. Background planning with learned models is often worse than model-free alternatives,...

Fall 2011

Maei, Hamid Reza

We present a new family of gradient temporal-difference (TD) learning methods with function approximation whose complexity, both in terms of memory and per-time-step computation, scales linearly with the number of learning parameters. TD methods are powerful prediction techniques, and with...

Spring 2024

Patterson, Andrew

In this thesis, we seek to improve the reliability of reinforcement learning algorithms for nonlinear function approximation. Semi-gradient temporal difference (TD) update rules form the basis of most state-of-the-art value function learning systems despite clear counterexamples proving their...

Fall 2022

Liu, Puer

We have witnessed the rising popularity of real-world applications of reinforcement learning (RL). However, most successful real-world applications of RL rely on high-fidelity simulators that enable rapid iteration of prototypes, hyperparameter selection and policy training. On the other hand, RL...