Matching Items (2)
Filtering by

Clear all filters

133880-Thumbnail Image.png

ReL GoalD (Reinforcement Learning for Goal Dependencies)

Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form…

In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
133401-Thumbnail Image.png

Development of a Game of Logic for Investigating of Trust in Human Robot Interaction

Description
As robotics technology advances, robots are being created for use in situations where they collaborate with humans on complex tasks.  For this to be safe and successful, it is important to understand what causes humans to trust robots more or less during a collaborative task.  This research project aims to…

As robotics technology advances, robots are being created for use in situations where they collaborate with humans on complex tasks.  For this to be safe and successful, it is important to understand what causes humans to trust robots more or less during a collaborative task.  This research project aims to investigate human-robot trust through a collaborative game of logic that can be played with a human and a robot together. This thesis details the development of a game of logic that could be used for this purpose. The game of logic is based upon a popular game in AI research called ‘Wumpus World’. The original Wumpus World game was a low-interactivity game to be played by humans alone. In this project, the Wumpus World game is modified for a high degree of interactivity with a human player, while also allowing the game to be played simultaneously by an AI algorithm.
ContributorsBoateng, Andrew Owusu (Author) / Sodemann, Angela (Thesis director) / Martin, Thomas (Committee member) / Software Engineering (Contributor) / Engineering Programs (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05