Search

Fall 2024

Roice, Kevin

Planning and goal-conditioned reinforcement learning aim to create more efficient and scalable methods for complex, long-horizon tasks. These approaches break tasks into manageable subgoals and leverage prior knowledge to guide learning. However, learned models may predict inaccurate next states...

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 2020

Chan, Alan

Policy gradient methods typically estimate both explicit policy and value functions. The long-extant view of policy gradient methods as approximate policy iteration---alternating between policy evaluation and policy improvement by greedification---is a helpful framework to elucidate algorithmic...

Spring 2023

Shah, Haseeb

Gradient Descent algorithms suffer many problems when learning representations using fixed neural network architectures, such as reduced plasticity on non-stationary continual tasks and difficulty training sparse architectures from scratch. A common workaround is continuously adapting the neural...

Fall 2021

Hashemzadeh, Maryam

The representations generated by many models of language (word embeddings, recurrent neural networks and transformers) correlate to brain activity recorded while people listen. However, these decoding results are usually based on the brain’s reaction to syntactically and semantically sound...

Fall 2021

Pan, Yangchen

A common scientific challenge for putting a reinforcement learning agent into practice is how to improve sample efficiency as much as possible with limited computational or memory resources. Such available physical resources may vary in different applications. My thesis introduces some approaches...

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...

Spring 2020

Farzane Aminmansour

Mapping the macrostructural connectivity of the living human brain is one of the primary goals of neuroscientists who study connectomics. The reconstruction of a brain's structural connectivity, aka its connectome, typically involves applying expert analysis to diffusion-weighted magnetic...

Fall 2024

Mesbahi, Golnaz

If we aspire to design algorithms that can run for long periods, continually adapting to new, unexpected situations, then we must be willing to deploy our agents without tuning their hyperparameters over the agent’s entire lifetime. The standard practice in deep RL—and even continual RL—is to...

Fall 2023

Schlegel, Matthew K

Partial observability---when the senses lack enough detail to make an optimal decision---is the reality of any decision making agent acting in the real world. While an agent could be made to make due with its available senses, taking advantage of the history of senses can provide more context and...