This dissertation explores algorithms for learning ranking functions to efficiently solve search problems, with application to automated planning. Specifically, we consider the frameworks of beam search, greedy search, and randomized search, which all aim to maintain tractability at the cost of not guaranteeing completeness nor optimality. Our learning objective for...
This thesis focuses on the problem of object tracking. Given a video, the general objective of tracking is to track the location over time of one or more targets in the image sequence. This is a very challenging task as algorithms need to deal with problems such as appearance variations,...
Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics...
Dynamic bipedal locomotion is among the most difficult and yet relevant problems in modern robotics. While a multitude of classical control methods for bipedal locomotion exist, they are often brittle or limited in capability. In recent years, work in applying reinforcement learning to robotics has lead to superior performance across...
Anomaly detection has been used in variety of applications in practice, including cyber-security, fraud detection and detecting faults in safety critical systems, etc. Anomaly detectors produce a ranked list of statistical anomalies, which are typically examined by human analysts in order to extract the actual anomalies of interest. Unfortunately, most...
Domain-independent automated planning is concerned with computing a sequence of actions that can transform an initial state into a desired goal state. Resource production domains form an interesting class of such problems, in that they typically require reasoning about concurrent durative-actions with continuous effects while minimizing some cost function. Although...
Monte-Carlo planning algorithms such as UCT make decisions at each step by
intelligently expanding a single search tree given the available time and then
selecting the best root action. Recent work has provided evidence that it can be
advantageous to instead construct an ensemble of search trees and make a...
Monte-Carlo Tree Search (MCTS) is an online-planning algorithm for decision-theoretic planning in domains with stochastic and combinatorial structure. The general applicability of MCTS makes it an ideal first choice to investigate when developing planners for complex applications requiring automated control and planning. The first contribution of this thesis is to...
Expensive pricing for laboratory bioreactors proves to be the main barrier-to-entry for lab-scale academic research. Most laboratory bioreactors are priced at $100K+ and require significant training to use, thereby limiting their accessibility. The IDEAL (Intuitive, Developmental And Research Oriented, Easy To Use, Affordable, And Low Volume) Bioreactor aims to solve...