Search

Spring 2024

Carvalho, Tales Henrique

Searching for programmatic policies to solve a reinforcement learning problem can be challenging, particularly when dealing with domain-specific languages (DSLs) that define policies with internal states for partially observable Markov decision processes (POMDPs). This is because they lead to...

Fall 2024

Tjhia, Kenneth G

This thesis empirically investigates the comparative ease of learning policies and heuristics for bidirectional versus unidirectional search in satisficing classical planning. Our research explores the potential advantages of bidirectional search in terms of learnability and efficiency of the...

Fall 2024

Sadmine, Quazi Asif

Despite having advantages such as generalizability and interpretability over neural representations, programmatic representations of hypotheses and strategies face significant challenges. This is because algorithms writing programs encoding hypotheses for solving supervised learning problems and...

Fall 2024

Bashir, Zahra

Although the synthesis of programs encoding policies often carries the promise of interpretability, systematic evaluations were never performed to assess the interpretability of these policies, likely because of the complexity of such an evaluation. In this dissertation, we introduce a novel...

Spring 2023

Ameen, Saqib

Cost-guided bottom-up search (BUS) algorithms use a cost function to guide the search for solving program synthesis tasks. In this thesis, we show that current state-of-the-art cost-guided BUS algorithms suffer from a common problem: they can lose useful information given by the model and fail to...

Spring 2024

Alikhasi, Mahdi

In reinforcement learning, agents solve problems through interactions with the environment. However, when faced with intricate environmental dynamics, learning can become challenging, resulting in sub-optimal policies. A potential remedy to this situation lies in the transfer of knowledge from...

Fall 2023

Rahman, Habibur

Program synthesis faces a significant challenge in exploring a vast program space to find a program that satisfies the user's intent. Prior studies have proposed using different methods to guide the synthesis process to address this challenge. We propose a method that offers search guidance which...