Learning from Stories: Using Natural Communication to Train Believable Agents
نویسندگان
چکیده
In this work we introduce Quixote, a system that allows non-programmers to train believable virtual agents and robots using the sociocultural knowledge present in stories. Quixote uses a corpus of exemplar stories to engineer a reward function that can be used to train virtual agents to exhibit desired behaviors using reinforcement learning. We show the effectiveness of our system with a case study in a modified gridworld environment called Pharmacy World. In this case study, we examine the performance of Quixote under ideal conditions and evaluate how humans perceive the policies that our system produces. In addition, we examine how Quixote performs in this environment when ambiguities in natural language correspondence causes difficulty in mapping story events to agent actions.
منابع مشابه
Towards Learning From Stories: An Approach to Interactive Machine Learning
In this work, we introduce a technique that uses stories to train virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy Wor...
متن کاملLearning From Stories: Using Crowdsourced Narratives to Train Virtual Agents
In this work we introduce Quixote, a system that makes programming virtual agents more accessible to nonprogrammers by enabling these agents to be trained using the sociocultural knowledge present in stories. Quixote uses a corpus of exemplar stories to automatically engineer a reward function that is used to train virtual agents to exhibit desired behaviors using reinforcement learning. We sho...
متن کاملData-Driven Alibi Story Telling for Social Believability
As computer games adopt larger, more life-like virtual worlds, socially believable characters become progressively more important. Socially believable non-player characters (NPCs) must be able to act in social situations and communicate with human players. In this paper, we address one aspect of social believability: the construction and telling of alibi stories, or an artificial background tha...
متن کاملRunning head: PSYCHOLOGICALLY BELIEVABLE AGENTS
PSYCHOLOGICALLY BELIEVABLE AGENTS 2 Summary Embodied conversational agents (ECAs) are designed to provide a natural and intuitive communication with a human user. One current major topic in agent design consequently is to enhance their believability, often by means of incorporating internal models of emotions or motivations. As psychological theories often lack the necessary details for a direct
متن کاملTowards a Narrative Mind: The Creation of Coherent Life Stories for Believable Virtual Agents
This paper describes an approach to create coherent life stories for Intelligent Virtual Agents (IVAs) in order to achieve long-term believability. We integrate a computational autobiographic memory, which allows agents to remember significant past experiences and reconstruct their life stories from these experiences, into an emotion-driven planning architecture. Starting from the literature re...
متن کامل