Search Constraints

Start Over
Filtering by: Creator Rossignol, P. A. Remove constraint Creator: Rossignol, P. A. Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • 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:
    Constraints for Sequential Decision Making Abstract approved: Alan P. Fern Writing a program that performs

  • 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

  • Monte Carlo Tree Search with Fixed and Adaptive Abstractions

    Creator:
    Hostetler, Jesse A.
    Abstract:
    Monte Carlo tree search (MCTS) is a class of online planning algorithms for Markov decision processes (MDPs) and related models that has found success in challenging applications. In the online planning approach, the agent makes a decision in the current state by performing a limited forward search over possible futures...
    Resource Type:
    Dissertation
    Full Text:
    uncertainty. We consider MDPs of the formM = 〈S,A, P,R, γ〉, where S andA are finite sets of states and

  • Scheduling and Online Planning in Stochastic Diffusion Networks

    Creator:
    Xue, Shan
    Abstract:
    Diffusion processes in networks are common models for many domains, including species colonization, information/idea cascade, disease propagation and fire spreading. In diffusion networks, a diffusion event occurs when a behavior spreads from one node to the other following a probabilistic model, where the behavior could be species, an idea, a...
    Resource Type:
    Dissertation
    Full Text:
    facilitate nesting. Each parcel p has a cost c(p), which denotes the cost of purchasing the land and

  • 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:
    an d A ta ri en v ir on m en ts . G am e Q B N S iz es O ri gi n al M M A ft er P ru

  • New learning modes for sequential decision making

    Creator:
    Judah, Kshitij
    Abstract:
    This thesis considers the problem in which a teacher is interested in teaching action policies to computer agents for sequential decision making. The vast majority of policy learning algorithms o er teachers little flexibility in how policies are taught. In particular, one of two learning modes is typically considered: 1)...
    Resource Type:
    Dissertation
    Full Text:
    Modes for Sequential Decision Making Abstract approved: Alan P. Fern This thesis considers the

  • Adiabatic Markov Decision Process : convergence of value iteration algorithm

    Creator:
    Duong, Thai
    Abstract:
    Markov Decision Process (MDP) is a well-known framework for devising the optimal decision making strategies under uncertainty. Typically, the decision maker assumes a stationary environment which is characterized by a time-invariant transition probability matrix. However, in many real-world scenarios, this assumption is not justified, thus the optimal strategy might not...
    Resource Type:
    Masters Thesis
    Full Text:
    are characterized by a time-invariant transition probability matrix P. 3 1.2 Non-stationary

  • Toward computer vision for understanding American football in video

    Creator:
    Hess, Robin W.
    Abstract:
    In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...
    Resource Type:
    Dissertation
    Full Text:
    Vision for Understanding American Football in Video Abstract approved: Alan P. Fern In this work, I

  • Data Collection in Sensor Networks via the Novel Fast Markov Decision Process Framework

    Creator:
    Duong, Thai
    Abstract:
    We investigate the data collection problem in sensor networks. The network consists of a number of stationary sensors deployed at different sites for sensing and storing data locally. A mobile element moves from sites to sites to collect data from the sensors periodically. There are different costs associated with the...
    Resource Type:
    Masters Thesis
    Full Text:
    of the system, a set of control actions A, a transition probability matrix P|S|×|S|, and a reward

  • 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:
    produces a probability distribution over actions, P (a|s), which we will denote by the vector P̂ (s). Given