Search Constraints

Start Over
Filtering by: Creator Vroom, Peter S. Remove constraint Creator: Vroom, Peter S. Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • Effectiveness of integration of internet technologies in support of teaching and learning computer science programming

    Creator:
    Hajebi, Mojgan
    Abstract:
    In spite of wide spread adoption of the internet technology in teaching and learning, little research exists on the use and the effect of web incorporation in teaching and learning. Immediate clarification of how, when, and for whom the web integration in education is beneficial is needed. This qualitative study...
    Resource Type:
    Dissertation
    Full Text:
    , Professors Peter Clark, Dianne Erickson, Prasad Tadepalli, and Norman Lederman for their ongoing guidance

  • 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:
    , Prof. N. S. Narayanaswamy and Prof. Deepak Khemani at IIT Madras, and Prof. Anselm Blumer at Tufts

  • Simulator-Defined MDP Planning with Applications in Natural Resource Management

    Creator:
    Alkaee Taleghan, Majid
    Abstract:
    This work is inspired by problems in natural resource management centered on the challenge of invasive species. Computing optimal management policies for maintaining ecosystem sustainable is challenging. Many ecosystem management problems can be formulated as MDP (Markov Decision Process) planning problems. In a simulator-defined MDP, the Markovian dynamics and rewards...
    Resource Type:
    Dissertation
    Full Text:
    Fiechter(s0, γ, F, �, δ) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2 UPPERP(s, a, δ

  • Analytical Methods for Improving Causal Inference

    Creator:
    Sinha, Meghamala
    Abstract:
    Causal inference is an important analytical tool to bridge the gap between prediction and decision-making. However, learning a causal network solely from data is a challenging task. In this work, various techniques have been explored for a better and improved causal network learning from data. Firstly, the problem of learning...
    Resource Type:
    Dissertation
    Full Text:
    network. The network type is as follows: RW, real-world; S, synthetic. . . . . . . . . . . . . . . 43 3.1

  • 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:
    ) HalfCheetah and b) Maze2d-Open. For each PCQ (s, π, ŝ, π̂, h), we plot V π(s, h) vs. V π̂(ŝ, h

  • Interpretable Machine Learning: Applications in Biology and Genomics

    Creator:
    Danaee, Padideh
    Abstract:
    Machine learning (ML) and deep learning (DL) models impact our daily lives with applications in natural language modeling, image analysis, healthcare, genomics, and bioinformatics. The exponential growth of biological sequence data necessitates accompanying advances in computational methods. Although deep learning is highly effective for detecting and classifying biological sequences, challenges...
    Resource Type:
    Dissertation
    Full Text:
    solution for path graphs. 107 4 MaxFirstPagePairs(S,L) algorithm uses a bottom-up CKY-approach to

  • Incorporating and Learning Behavior Constraints for Sequential Decision Making

    Creator:
    Pinto, Jervis
    Abstract:
    Writing a program that performs well in a complex environment is a challenging task. In such problems, a method of deterministic programming combined with reinforcement learning (RL) can be helpful. However, current systems either force developers to encode knowledge in very specific forms (e.g., state-action features), or assume advanced RL...
    Resource Type:
    Dissertation
    Full Text:
    Problems (MDPs) In the setting considered here, an MDP [52] is a tuple (S,A, P,R), where S is a finite set

  • 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:
    [18]’s depth prediction task to our setting – significantly altering the architecture to fit the

  • Variational Satisfiability Solving

    Creator:
    Young, Jeffrey M.
    Abstract:
    Over the last two decades, satisfiability and satisfiability-modulo theory (SAT/SMT) solvers have grown powerful enough to be general purpose reasoning engines throughout software engineering and computer science. However, most practical use cases of SAT/SMT solvers require not just solving a single SAT/SMT problem, but solving sets of related SAT/SMT problems....
    Resource Type:
    Dissertation
    Full Text:
    shared elements and one to sum the rest. With this procedure the summation of ns is ∑ n∈ns n = ∑ s∈ss

  • 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:
    collaborations and Peter Anderson and Jesse Thomason for their advising insights and generosity. I thank the