Search Constraints

Start Over
Filtering by: Creator Sutton, Shan C. Remove constraint Creator: Sutton, Shan C. Advisor Tadepalli, Prasad Remove constraint Advisor: Tadepalli, Prasad

Search Results

  • Effective decision-theoretic assistance through relational hierarchical models

    Creator:
    Natarajan, Sriraam
    Abstract:
    Building intelligent computer assistants has been a long-cherished goal of AI. Many intelligent assistant systems were built and fine-tuned to specific application domains. In this work, we develop a general model of assistance that combines three powerful ideas: decision theory, hierarchical task models and probabilistic relational languages. We use the...
    Resource Type:
    Dissertation
    Full Text:
    model in a real-world activity recognition task. c©Copyright by Sriraam Natarajan November 20, 2007

  • 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:
    cards is known, solving more than 82% of games. c©Copyright by Ronald Vance Bjarnason, Jr. December

  • Scaling multiagent reinforcement learning

    Creator:
    Proper, Scott
    Abstract:
    Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity or "outcome space" explosion. Multiagent domains are particularly susceptible to these problems. This thesis describes ways to mitigate these curses in several different multiagent domains, including real-time delivery of products...
    Resource Type:
    Dissertation
    Full Text:
    . c©Copyright by Scott Proper December 1, 2009 All Rights Reserved Scaling Multiagent

  • Hierarchical structure discovery and transfer in sequential decision problems

    Creator:
    Mehta, Neville
    Abstract:
    Acting intelligently to efficiently solve sequential decision problems requires the ability to extract hierarchical structure from the underlying domain dynamics, exploit it for optimal or near-optimal decision-making, and transfer it to related problems instead of solving every problem in isolation. This dissertation makes three contributions toward this goal. The first...
    Resource Type:
    Dissertation
    Full Text:
    error. A general action-modeling language is shown to be efficiently learnable in both frameworks. c

  • Hierarchical average reward reinforcement learning

    Creator:
    Seri, Sandeep
    Abstract:
    Reinforcement Learning (RL) is the study of agents that learn optimal behavior by interacting with and receiving rewards and punishments from an unknown environment. RL agents typically do this by learning value functions that assign a value to each state (situation) or to each state-action pair. Recently, there has been...
    Resource Type:
    Masters Thesis
    Full Text:
    , 2001; Moore, Baird, & Kaelbling, 1999; Parr & Russell, 1998: Sutton, Precup, & Singh, 1999), is to use

  • Bayesian methods for knowledge transfer and policy search in reinforcement learning

    Creator:
    Wilson, Aaron
    Abstract:
    How can an agent generalize its knowledge to new circumstances? To learn effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
    Resource Type:
    Dissertation
    Full Text:
    active learning strategy generally improves the speed of learning. c©Copyright by Aaron Wilson July

  • A study of model-based average reward reinforcement learning

    Creator:
    Ok, DoKyeong
    Abstract:
    Reinforcement Learning (RL) is the study of learning agents that improve their performance from rewards and punishments. Most reinforcement learning methods optimize the discounted total reward received by an agent, while, in many domains, the natural criterion is to optimize the average reward per time step. In this thesis, we...
    Resource Type:
    Dissertation
    Full Text:
    executed recently in a given state (Sutton, 1990). 2.3. Dynamic Programming Given a complete and

  • 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:
    cost function C and returns the minimum-cost solution. There are three key learning challenges in this

  • Domain-Independent Planning for Markov Decision Processes with Factored State and Action Spaces

    Creator:
    Raghavan, Aswin
    Abstract:
    Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...
    Resource Type:
    Dissertation
    Full Text:
    improves upon the responsiveness of the baseline that dispatches the nearest responders. c©Copyright by

  • High-Dimensional Reinforcement Learning with Human Feedback

    Creator:
    Curran, William
    Abstract:
    State-of-the-art personal robots need to perform complex manipulation tasks to be viable in complex scenarios. However, many of these robots, like the PR2, use manipulators with high degrees of freedom. High degrees of freedom are desirable from a functionality standpoint, but make the learning task more difficult by adding a...
    Resource Type:
    Dissertation
    Full Text:
    interface that uses this timeline interface paradigm. c©Copyright by William Curran June 5, 2017 All