Search Constraints

Start Over
Filtering by: Creator Fern, Alan Remove constraint Creator: Fern, Alan

Search Results

  • 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:
    Abstract approved: Alan Fern Papers proposing novel machine learning algorithms tend to present the

  • Robust Reference-Free Sim-to-Real Reinforcement Learning for Bipedal Locomotion

    Creator:
    Siekmann, Jonah A.
    Abstract:
    In recent years, model-free Deep Reinforcement Learning (RL) has become an increasingly popular alternative to more traditional model-based or optimization-based control methods in solving robotic legged locomotion. However, deploying RL in the real world can be a significant undertaking. Constructing reward functions which compel controllers to learn the desired behavior...
    Resource Type:
    Masters Thesis
    Full Text:
    -Free Sim-to-Real Reinforcement Learning for Bipedal Locomotion Abstract approved: Alan Fern In

  • Solving Physical Reasoning Tasks in Simulated Environments

    Creator:
    Shureih, Zeyad
    Abstract:
    We take for granted how quickly we, as humans, form mental models of the world around us. By the time we are toddlers, we have an observable intuition around the physical rules of the world. Stacking blocks such that they don’t fall over becomes such a trivial task, that it...
    Resource Type:
    Honors College Thesis
    Full Text:
    : ____________________________________________________ Alan Fern Key Words: machine common sense, computer vision, physical reasoning, physics engines

  • Ensemble Monte-Carlo planning : an empirical study

    Creator:
    Lewis, Paul
    Abstract:
    Monte-Carlo planning algorithms such as UCT make decisions at each step by intelligently expanding a single search tree given the available time and then selecting the best root action. Recent work has provided evidence that it can be advantageous to instead construct an ensemble of search trees and make a...
    Resource Type:
    Masters Thesis
    Full Text:
    Planning: An Empirical Study Abstract approved: Alan Fern Monte-Carlo planning algorithms such as UCT

  • 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

  • Learning ranking functions for efficient search

    Creator:
    Xu, Yuehua
    Abstract:
    This dissertation explores algorithms for learning ranking functions to efficiently solve search problems, with application to automated planning. Specifically, we consider the frameworks of beam search, greedy search, and randomized search, which all aim to maintain tractability at the cost of not guaranteeing completeness nor optimality. Our learning objective for...
    Resource Type:
    Dissertation
    Full Text:
    : Alan Fern This dissertation explores algorithms for learning ranking functions to efficiently solve

  • Automatically Generating Solutions for Sokoban Maps

    Creator:
    Greco, Jason Aaron
    Abstract:
    Generating solutions to Sokoban levels is an NP-hard problem that is difficult for even modern day computers to solve due to its complexity. This project explores the creation of a Sokoban solver by eliminating as many potential moves as possible to greatly limit the overall search space. This reduction is...
    Resource Type:
    Honors College Thesis
    Full Text:
    : ______________________________________________________ Alan Fern Generating solutions to Sokoban levels is an NP-hard problem that is

  • Offensive Direction Inference in Real-World Football Video

    Creator:
    Lu, Qingkai
    Abstract:
    Automatic analysis of American football videos can help teams develop strategies and extract patterns with less human effort. In this work, we focus on the problem of automatically determining which team is on offense/defense, which is an important subproblem for higher-level analysis. While seemingly mundane, this problem is quite challenging...
    Resource Type:
    Masters Thesis
    Full Text:
    approved: Alan P. Fern Automatic analysis of American football videos can help teams develop strategies

  • Recurrent Neural Networks for Robotic Control of a Human-Scale Bipedal Robot

    Creator:
    Siekmann, Jonah A.
    Abstract:
    Dynamic bipedal locomotion is among the most difficult and yet relevant problems in modern robotics. While a multitude of classical control methods for bipedal locomotion exist, they are often brittle or limited in capability. In recent years, work in applying reinforcement learning to robotics has lead to superior performance across...
    Resource Type:
    Honors College Thesis
    Full Text:
    Bipedal Robot Abstract approved: Alan Fern Dynamic bipedal locomotion is among the most difficult and

  • Practical Reinforcement Learning for Bipedal Locomotion

    Creator:
    Dao, Jeremy
    Abstract:
    Reinforcement learning has emerged as a popular tool for solving control tasks, with multiple works focusing on the complex and dynamic task of locomotion. However, the naive application of reinforcement learning to this problem often produces maladaptive policies that exploit the model or reward function. This results in behavior that...
    Resource Type:
    Capstone Project
    Full Text:
    : Alan Fern Abstract - Reinforcement learning has emerged as a popular tool for solving control tasks