Search Constraints

Start Over
Filtering by: Creator Schreiber, Alan S. Remove constraint Creator: Schreiber, Alan S. Committee Member Wong, Weng-Keen Remove constraint Committee Member: Wong, Weng-Keen Rights Statement In Copyright Remove constraint Rights Statement: In Copyright

Search Results

  • 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:
    approved: Alan Fern Learning latent space representations of high-dimensional world states has been at

  • UCT for tactical assault battles in real-time strategy games

    Creator:
    Balla, Radha-Krishna
    Abstract:
    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...
    Resource Type:
    Masters Thesis
    Full Text:
    Alan Fern We consider the problem of tactical assault planning in real-time strategy games

  • A SAT-based planning framework for optimizing resource production

    Creator:
    Ventura, Christopher
    Abstract:
    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...
    Resource Type:
    Masters Thesis
    Full Text:
    Production Abstract approved: Alan Fern Domain-independent automated planning is concerned with computing

  • Revisiting output coding for sequential supervised learning

    Creator:
    Hao, Guohua
    Abstract:
    Markov models are commonly used for joint inference of label sequences. Unfortunately, inference scales quadratically in the number of labels, which is problematic for training methods where inference is repeatedly preformed and is the primary computational bottleneck for large label sets. Recent work has used output coding to address this...
    Resource Type:
    Masters Thesis
    Full Text:
    Sequential Supervised Learning Abstract approved: Alan Fern Markov models are commonly used for joint

  • Re-understanding Finite-State Representations of Recurrent Policy Networks

    Creator:
    Danesh, Mohamad H.
    Abstract:
    We propose an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this problem by transforming such recurrent policy networks into finite-state machines (FSM) and then analyzing the equivalent minimized FSM. While this led to interesting insights, the minimization process can obscure a deeper understanding...
    Resource Type:
    Masters Thesis
    Full Text:
    -understanding Finite-State Representations of Recurrent Policy Networks Abstract approved: Alan P. Fern We

  • Monte-Carlo planning for probabilistic domains

    Creator:
    Bjarnason, Ronald V.
    Abstract:
    This thesis presents a progression of novel planning algorithms that culminates in a new family of diverse Monte-Carlo methods for probabilistic planning domains. We provide a proof for performance guarantees and analyze how these algorithms can resolve some of the shortcomings of traditional probabilistic planning methods. The direct policy search...
    Resource Type:
    Dissertation
    Full Text:
    , 2009. Title: Monte-Carlo Planning for Probabilistic Domains Abstract approved: Prasad Tadepalli Alan

  • Integrating learning and search for structured prediction

    Creator:
    Doppa, Janardhan Rao
    Abstract:
    We are witnessing the rise of the data-driven science paradigm, in which massive amounts of data - much of it collected as a side-effect of ordinary human activity - can be analyzed to make sense of the data and to make useful predictions. To fully realize the promise of this...
    Resource Type:
    Dissertation
    Full Text:
    : Integrating Learning and Search for Structured Prediction Abstract approved: Prasad Tadepalli Alan P. Fern

  • Adversarial planning by strategy switching in a real-time strategy game

    Creator:
    King, Brian D.
    Abstract:
    We consider the problem of strategic adversarial planning in a Real-Time Strategy (RTS) game. Strategic adversarial planning is the generation of a network of high-level tasks to satisfy goals while anticipating an adversary's actions. In this thesis we describe an abstract state and action space used for planning in an...
    Resource Type:
    Masters Thesis
    Full Text:
    : Adversarial Planning by Strategy Switching in a Real-Time Strategy Game Abstract approved: Alan P. Fern We

  • Active Learning from Examples, Queries and Explanations

    Creator:
    Hamidi-Haines, Mandana
    Abstract:
    Humans are remarkably efficient in learning by interacting with other people and observing their behavior. Children learn by watching their parents’ actions and mimic their behavior. When they are not sure about their parents demonstration, they communicate with them, ask questions, and learn from their feedback. On the other hand,...
    Resource Type:
    Dissertation
    Full Text:
    grateful for the opportunities that he gave me to travel, and attend the conferences. Professor Alan Fern

  • Open Set Learning with Counterfactual Images

    Creator:
    Neal, Lawrence W.
    Abstract:
    In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training. To detect unknown classes while still generalizing to new instances of existing classes, this thesis introduces a dataset augmentation technique called counterfactual image generation. This approach, based on...
    Resource Type:
    Masters Thesis
    Full Text:
    for which CK ’s prediction confidence is less than a fixed threshold maxi P (yi|xint) < φ are