Value Learning For Interactive Games Embodied Artificial Intelligence And Robotics
Download Value Learning For Interactive Games Embodied Artificial Intelligence And Robotics PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Value Learning For Interactive Games Embodied Artificial Intelligence And Robotics book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Value Learning for Interactive Games, Embodied Artificial Intelligence, and Robotics
Simulation plays a crucial role in modern academic study, particularly in the field of artificial intelligence (AI). The simulation environment can mimic real-world scenarios, allowing the AI agent to learn, adapt, and make decisions in a controlled and safe setting. This thesis tackles two important problems in building the next generation of artificial general intelligence (AGI): how to efficiently train an AI agent with values and how to overcome the simulation to reality gap to bring the training results to real-world applications. The current studies of AI mainly consider learning about the potential or energy function (U), referring to understanding the impact of the outside environment. The U function helps the agent apprehend the physical world laws, natural potentials, and social norms. However, taking into account the value learning, usually representing modeling one's inside thinking, benefits the agent to derive its goals, intents, and social values. Our research shows that both U and V learning are equally important to the pathway to AGI. The learning of U is usually data-driven. It enables the agent to imitate and complete the task through statistical learning. By incorporating the value function, the agent can spontaneously specify a task plan and its behavior is more in line with human cognition and value. This thesis consists of three parts: (1) Potential function learning, which explores the process of acquiring knowledge or skills that are useful and practical for a particular purpose. (2) Value learning when learning the potential (U) function can not satisfy all the learning goals, which investigates situations where utility-based learning approaches might be limited or ineffective. (3) Combining U and V learning, which focuses on the integration of simulation-based learning and data-driven learning methods. We primarily focus on assessing the effectiveness of U learning within a simulated environment. Our investigation commences with agents operating in a controlled simulated setting, where the action space is intentionally kept small. Through rigorous testing and iterative refinement, we gradually expand the scope of our analysis to encompass agents dealing with increasingly complex and continuous action spaces. Upon achieving compelling results in the simulated realm, we proceed to the crucial next step: transferring the knowledge and expertise gained from the well-trained agents in the simulation space to real-world scenarios. This process entails adapting the learned policies, strategies, and decision-making capabilities of the agents to navigate the intricacies and uncertainties of genuine environments.
Embodied Multi-Agent Systems
In recent years, embodied multi-agent systems, including multi-robots, have emerged as essential solution for demanding tasks such as search and rescue, environmental monitoring, and space exploration. Effective collaboration among these agents is crucial but presents significant challenges due to differences in morphology and capabilities, especially in heterogenous systems. While existing books address collaboration control, perception, and learning, there is a gap in focusing on active perception and interactive learning for embodied multi-agent systems. This book aims to bridge this gap by establishing a unified framework for perception and learning in embodied multi-agent systems. It presents and discusses the perception-action-learning loop, offering systematic solutions for various types of agents—homogeneous, heterogeneous, and ad hoc. Beyond the popular reinforcement learning techniques, the book provides insights into using fundamental models to tackle complex collaboration problems. By interchangeably utilizing constrained optimization, reinforcement learning, and fundamental models, this book offers a comprehensive toolkit for solving different types of embodied multi-agent problems. Readers will gain an understanding of the advantages and disadvantages of each method for various tasks. This book will be particularly valuable to graduate students and professional researchers in robotics and machine learning. It provides a robust learning framework for addressing practical challenges in embodied multi-agent systems and demonstrates the promising potential of fundamental models for scenario generation, policy learning, and planning in complex collaboration problems.
The Handbook on Socially Interactive Agents
The Handbook on Socially Interactive Agents provides a comprehensive overview of the research fields of Embodied Conversational Agents;Intelligent Virtual Agents;and Social Robotics. Socially Interactive Agents (SIAs);whether virtually or physically embodied;are autonomous agents that are able to perceive an environment including people or other agents;reason;decide how to interact;and express attitudes such as emotions;engagement;or empathy. They are capable of interacting with people and one another in a socially intelligent manner using multimodal communicative behaviors;with the goal to support humans in various domains. Written by international experts in their respective fields;the book summarizes research in the many important research communities pertinent for SIAs;while discussing current challenges and future directions. The handbook provides easy access to modeling and studying SIAs for researchers and students;and aims at further bridging the gap between the research communities involved. In two volumes;the book clearly structures the vast body of research. The first volume starts by introducing what is involved in SIAs research;in particular research methodologies and ethical implications of developing SIAs. It further examines research on appearance and behavior;focusing on multimodality. Finally;social cognition for SIAs is investigated using different theoretical models and phenomena such as theory of mind or pro-sociality. The second volume starts with perspectives on interaction;examined from different angles such as interaction in social space;group interaction;or long-term interaction. It also includes an extensive overview summarizing research and systems of human–agent platforms and of some of the major application areas of SIAs such as education;aging support;autism;and games.