Search Constraints

Start Over
Filtering by: Creator Olden, Julian D. Remove constraint Creator: Olden, Julian D. Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • Machine learning for improving the quality of citizen science data

    Creator:
    Yu, Jun
    Abstract:
    Citizen Science is a paradigm in which volunteers from the general public participate in scientific studies, often by performing data collection. This paradigm is especially useful if the scope of the study is too broad to be performed by a limited number of trained scientists. Although citizen scientists can contribute...
    Resource Type:
    Dissertation
    Full Text:
    : (a) observer, (b) location, (c) visit, and (d) species. Observer information (e.g. name, ID and

  • Auxiliary Tasks for Efficient Learning of Point-Goal Navigation

    Creator:
    Desai, Saurabh Satish
    Abstract:
    Top-performing approaches to embodied AI tasks like point-goal navigation often rely on training agents via reinforcement learning over tens of millions (or even billions) of experiential steps – learning neural agents that map directly from visual observations to actions. In this work, we question whether these extreme training durations are...
    Resource Type:
    Masters Thesis
    Full Text:
    prediction outperforms RGB-D . . . . . . . . . . . . . . . 20 6.4 Combining multiple auxiliary tasks

  • Investigating Latent State and Uncertainty Representations in Reinforcement Learning

    Creator:
    Koul, Anurag
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    transition for a depth d using mode action of current stochastic policy. c) MCTS iteratively extends a

  • Learning and Improving Policies for Probabilistic Planning Problems

    Creator:
    Issakkimuthu, Murugeswari
    Abstract:
    In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
    Resource Type:
    Dissertation
    Full Text:
    pairs (clear(A), on(A, B)) and (clear(C), on(C, D)) are seman- tically similar. Since nodes in the

  • Coordination for Scalable Multiple Robot Planning Under Temporal Uncertainty

    Creator:
    Marcon dos Santos, Gilberto
    Abstract:
    This dissertation incorporates coalition formation and probabilistic planning towards a domain-independent automated planning solution scalable to multiple heterogeneous robots in complex domains. The first research direction investigates the effectiveness of Task Fusion and introduces heuristics that improve task allocation and result in better quality plans, while requiring lower computational cost...
    Resource Type:
    Dissertation

  • Semantic embodied navigation : developing agents that navigate from language and vision

    Creator:
    Krantz, Jacob
    Abstract:
    Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
    Resource Type:
    Dissertation
    Full Text:
    Language Navigators From Discrete to Continuous Simulation 137 TABLE OF CONTENTS (Continued) Page D

  • Improving and Understanding Deep Models for Natural Language Comprehension

    Creator:
    Ghaeini, Reza
    Abstract:
    Natural Language Comprehension is a challenging domain of Natural Language Processing. To improve a model’s language comprehension/understanding, one approach would be to enrich the structure of the model to enhance its capability in learning the latent rules of the language. In this dissertation, we will first introduce several deep models...
    Resource Type:
    Dissertation
    Full Text:
    ) and (b,d,f) represent the normalized attention weights for Entailment, Neutral, and Contradiction

  • Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties

    Creator:
    Dodge, Jonathan E.
    Abstract:
    Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools (e.g., a professional auditor, a developer, and an end user all have different needs). We posit that it is possible to provide...
    Resource Type:
    Dissertation
    Full Text:
    the CNN Agent from Chapters 6 and 7 . . . . . . . . . . . . . 153 D What domain to study? StarCraft

  • Stake-Free Evaluations of Black-Box Optimization and Spatio-Temporal Graph Network Algorithms

    Creator:
    Merrill, Erich, III
    Abstract:
    Papers proposing novel machine learning algorithms tend to present the algorithm or technique in question in the best possible light. The standard practice is generally for authors to emphasize their proposed algorithms' performance in the precise setting where it is maximally impressive, often by only fully evaluating their best known...
    Resource Type:
    Dissertation
    Full Text:
    Background We consider optimizing an unknown function f : X → R where X is a compact d- dimensional subset

  • A General Purpose Agent-Based Blackboard Optimization Method Applied to Sodium Fast Reactor Design and Analysis

    Creator:
    Stewart, Ryan H.
    Abstract:
    We present a novel multi-objective optimization methodology built upon a multi-agent blackboard framework. This multi-agent blackboard system (MABS) synthesizes blackboard architectures, multi-agent environments, and optimization theory. The blackboard architecture creates the framework for initializing, storing, and solving a multi-objective optimization problem. Multiple agents allow for an optimization problem to be...
    Resource Type:
    Dissertation
    Full Text:
    create a vector of our design variables x = x1, x2, ..., xn, which make up the design space D, where D