Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
18,848
result(s) for
"Agents (artificial intelligence)"
Sort by:
Building intelligent systems : a guide to machine learning engineering
\"Produce a fully functioning Intelligent System that leverages machine learning and data from user interactions to improve over time and achieve success. This book teaches you how to build an Intelligent System from end to end and leverage machine learning in practice. You will understand how to apply your existing skills in software engineering, data science, machine learning, management, and program management to produce working systems.\"--Page 4 of cover.
Book
Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities
Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to enable agents to learn and perform tasks autonomously with superhuman performance. However, we consider RL as fundamentally a Human-in-the-Loop (HITL) paradigm, even when an agent eventually performs its task autonomously. In cases where the reward function is challenging or impossible to define, HITL approaches are considered particularly advantageous. The application of Reinforcement Learning from Human Feedback (RLHF) in systems such as ChatGPT demonstrates the effectiveness of optimizing for user experience and integrating their feedback into the training loop. In HITL RL, human input is integrated during the agent’s learning process, allowing iterative updates and fine-tuning based on human feedback, thus enhancing the agent’s performance. Since the human is an essential part of this process, we argue that human-centric approaches are the key to successful RL, a fact that has not been adequately considered in the existing literature. This paper aims to inform readers about current explainability methods in HITL RL. It also shows how the application of explainable AI (xAI) and specific improvements to existing explainability approaches can enable a better human-agent interaction in HITL RL for all types of users, whether for lay people, domain experts, or machine learning specialists. Accounting for the workflow in HITL RL and based on software and machine learning methodologies, this article identifies four phases for human involvement for creating HITL RL systems: (1) Agent Development, (2) Agent Learning, (3) Agent Evaluation, and (4) Agent Deployment. We highlight human involvement, explanation requirements, new challenges, and goals for each phase. We furthermore identify low-risk, high-return opportunities for explainability research in HITL RL and present long-term research goals to advance the field. Finally, we propose a vision of human-robot collaboration that allows both parties to reach their full potential and cooperate effectively.
Journal Article
Social machines : the coming collision of artificial intelligence, social networking, and humanity
\"Will your next doctor be a human being-or a machine? Will you have a choice? If you do, what should you know before making it? This book introduces the reader to the pitfalls and promises of artificial intelligence in its modern incarnation and the growing trend of systems to 'reach off the Web' into the real world.\"--Publisher's description.
Book
Distributed Constraint Optimization Problems and Applications: A Survey
The field of multi-agent system (MAS) is an active area of research within artificial intelligence, with an increasingly important impact in industrial and other real-world applications. In a MAS, autonomous agents interact to pursue personal interests and/or to achieve common objectives. Distributed Constraint Optimization Problems (DCOPs) have emerged as a prominent agent model to govern the agents' autonomous behavior, where both algorithms and communication models are driven by the structure of the specific problem. During the last decade, several extensions to the DCOP model have been proposed to enable support of MAS in complex, real-time, and uncertain environments. This survey provides an overview of the DCOP model, offering a classification of its multiple extensions and addressing both resolution methods and applications that find a natural mapping within each class of DCOPs. The proposed classification suggests several future perspectives for DCOP extensions and identifies challenges in the design of efficient resolution algorithms, possibly through the adaptation of strategies from different areas.
Journal Article
The rise and potential of large language model based agents: a survey
For a long time, researchers have sought artificial intelligence (AI) that matches or exceeds human intelligence. AI agents, which are artificial entities capable of sensing the environment, making decisions, and taking actions, are seen as a means to achieve this goal. Extensive efforts have been made to develop AI agents, with a primary focus on refining algorithms or training strategies to enhance specific skills or particular task performance. The field, however, lacks a sufficiently general and powerful model to serve as a foundation for building general agents adaptable to diverse scenarios. With their versatile capabilities, large language models (LLMs) pave a promising path for the development of general AI agents, and substantial progress has been made in the realm of LLM-based agents. In this article, we conduct a comprehensive survey on LLM-based agents, covering their construction frameworks, application scenarios, and the exploration of societies built upon LLM-based agents. We also conclude some potential future directions and open problems in this flourishing field.
Journal Article
Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: A Short Survey
Building autonomous machines that can explore open-ended environments, discover possible interactions and build repertoires of skills is a general objective of artificial intelligence. Developmental approaches argue that this can only be achieved by autotelic agents: intrinsically motivated learning agents that can learn to represent, generate, select and solve their own problems. In recent years, the convergence of developmental approaches with deep reinforcement learning (RL) methods has been leading to the emergence of a new field: developmental reinforcement learning. Developmental RL is concerned with the use of deep RL algorithms to tackle a developmental problem— the intrinsically motivated acquisition of open-ended repertoires of skills. The self-generation of goals requires the learning of compact goal encodings as well as their associated goal-achievement functions. This raises new challenges compared to standard RL algorithms originally designed to tackle pre-defined sets of goals using external reward signals. The present paper introduces developmental RL and proposes a computational framework based on goal-conditioned RL to tackle the intrinsically motivated skills acquisition problem. It proceeds to present a typology of the various goal representations used in the literature, before reviewing existing methods to learn to represent and prioritize goals in autonomous systems. We finally close the paper by discussing some open challenges in the quest of intrinsically motivated skills acquisition.
Journal Article
The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care
Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals
1
–
3
, but the best treatment strategy remains uncertain. In particular, evidence suggests that current practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients
1
,
4
–
6
. To tackle this sequential decision-making problem, we developed a reinforcement learning agent, the Artificial Intelligence (AI) Clinician, which extracted implicit knowledge from an amount of patient data that exceeds by many-fold the life-time experience of human clinicians and learned optimal treatment by analyzing a myriad of (mostly suboptimal) treatment decisions. We demonstrate that the value of the AI Clinician’s selected treatment is on average reliably higher than human clinicians. In a large validation cohort independent of the training data, mortality was lowest in patients for whom clinicians’ actual doses matched the AI decisions. Our model provides individualized and clinically interpretable treatment decisions for sepsis that could improve patient outcomes.
A reinforcement learning agent, the AI Clinician, can assist physicians by providing individualized and clinically interpretable treatment decisions to improve patient outcomes.
Journal Article
Multi-agent deep reinforcement learning: a survey
The advances in reinforcement learning have recorded sublime success in various domains. Although the multi-agent domain has been overshadowed by its single-agent counterpart during this progress, multi-agent reinforcement learning gains rapid traction, and the latest accomplishments address problems with real-world complexity. This article provides an overview of the current developments in the field of multi-agent deep reinforcement learning. We focus primarily on literature from recent years that combines deep reinforcement learning methods with a multi-agent scenario. To survey the works that constitute the contemporary landscape, the main contents are divided into three parts. First, we analyze the structure of training schemes that are applied to train multiple agents. Second, we consider the emergent patterns of agent behavior in cooperative, competitive and mixed scenarios. Third, we systematically enumerate challenges that exclusively arise in the multi-agent domain and review methods that are leveraged to cope with these challenges. To conclude this survey, we discuss advances, identify trends, and outline possible directions for future work in this research area.
Journal Article
How does artificial intelligence in radiology improve efficiency and health outcomes?
Since the introduction of artificial intelligence (AI) in radiology, the promise has been that it will improve health care and reduce costs. Has AI been able to fulfill that promise? We describe six clinical objectives that can be supported by AI: a more efficient workflow, shortened reading time, a reduction of dose and contrast agents, earlier detection of disease, improved diagnostic accuracy and more personalized diagnostics. We provide examples of use cases including the available scientific evidence for its impact based on a hierarchical model of efficacy. We conclude that the market is still maturing and little is known about the contribution of AI to clinical practice. More real-world monitoring of AI in clinical practice is expected to aid in determining the value of AI and making informed decisions on development, procurement and reimbursement.
Journal Article