Research at the Interaction Lab focuses on human-agent communication using conversational Natural Language. The ultimate goal is to create systems where humans and AI agents (including embodied robots) can spontaneously form teams and coordinate shared tasks through the use of Natural Language conversation as a universal communication interface. This paper first introduces machine learning approaches to problems in conversational AI in general, where computational agents must coordinate with humans to solve tasks using conversational Natural Language. It also covers some of the practical systems developed in the Interaction Lab, ranging from speech interfaces on smart speakers to embodied robots interacting using visually grounded language. In several cases communication between multiple agents is addressed. The paper surveys the central research problems addressed here, the approaches developed, and our main results. Some key open research questions and directions are then discussed, leading towards a future vision of conversational, collaborative multi-agent systems.
{"title":"Conversational AI for multi-agent communication in Natural Language","authors":"Oliver Lemon","doi":"10.3233/aic-220147","DOIUrl":"https://doi.org/10.3233/aic-220147","url":null,"abstract":"Research at the Interaction Lab focuses on human-agent communication using conversational Natural Language. The ultimate goal is to create systems where humans and AI agents (including embodied robots) can spontaneously form teams and coordinate shared tasks through the use of Natural Language conversation as a universal communication interface. This paper first introduces machine learning approaches to problems in conversational AI in general, where computational agents must coordinate with humans to solve tasks using conversational Natural Language. It also covers some of the practical systems developed in the Interaction Lab, ranging from speech interfaces on smart speakers to embodied robots interacting using visually grounded language. In several cases communication between multiple agents is addressed. The paper surveys the central research problems addressed here, the approaches developed, and our main results. Some key open research questions and directions are then discussed, leading towards a future vision of conversational, collaborative multi-agent systems.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"9 1","pages":"295-308"},"PeriodicalIF":0.8,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83509065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multi-agent systems have been a core research topic in artificial intelligence for several decades. A multi-agent system consists of multiple decision-making agents – which may be software-based AI systems, physically-embodied robots, or humans – which must interact in a shared environment in pursuit of their goals. Multi-agent systems research spans a range of technical problems, such as how to design planning and learning algorithms which enable agents to achieve their goals; how to design multi-agent systems to incentivise certain behaviours in agents; how information is communicated and propagated among agents; and how norms, conventions, and roles may emerge in multi-agent systems. A vast array of applications have been addressed using multi-agent method-ologies, including autonomous driving, multi-robot factories, automated trading, commercial games, automated tutoring, and robotic rescue teams. The purpose of this special issue is to showcase current multi-agent systems research led by university and industry groups based in the United Kingdom. Research groups and institutes in the UK which have significant activity in multi-agent systems research were invited to submit an article describing: (1) the technical problems in multi-agent systems tackled by the group (their core research agenda), including applications and industry collaboration; (2) the main approaches developed by the group and any key results achieved; and (3) important open challenges in multi-agent systems research from the perspective of the group. A large number of high-quality submissions were received, of which 14 were included for publication in the special issue. These articles represent a broad set of research topics within the field of multi-agent systems, showcasing the strength of contributions made by UK-based research groups in both universities and industry. We believe the open research problems discussed in each of the articles will provide a rich resource for researchers in this field, both new and old.
{"title":"Multi-agent systems research in the United Kingdom","authors":"Stefano V. Albrecht, M. Wooldridge","doi":"10.3233/aic-229003","DOIUrl":"https://doi.org/10.3233/aic-229003","url":null,"abstract":"Multi-agent systems have been a core research topic in artificial intelligence for several decades. A multi-agent system consists of multiple decision-making agents – which may be software-based AI systems, physically-embodied robots, or humans – which must interact in a shared environment in pursuit of their goals. Multi-agent systems research spans a range of technical problems, such as how to design planning and learning algorithms which enable agents to achieve their goals; how to design multi-agent systems to incentivise certain behaviours in agents; how information is communicated and propagated among agents; and how norms, conventions, and roles may emerge in multi-agent systems. A vast array of applications have been addressed using multi-agent method-ologies, including autonomous driving, multi-robot factories, automated trading, commercial games, automated tutoring, and robotic rescue teams. The purpose of this special issue is to showcase current multi-agent systems research led by university and industry groups based in the United Kingdom. Research groups and institutes in the UK which have significant activity in multi-agent systems research were invited to submit an article describing: (1) the technical problems in multi-agent systems tackled by the group (their core research agenda), including applications and industry collaboration; (2) the main approaches developed by the group and any key results achieved; and (3) important open challenges in multi-agent systems research from the perspective of the group. A large number of high-quality submissions were received, of which 14 were included for publication in the special issue. These articles represent a broad set of research topics within the field of multi-agent systems, showcasing the strength of contributions made by UK-based research groups in both universities and industry. We believe the open research problems discussed in each of the articles will provide a rich resource for researchers in this field, both new and old.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"1243 1","pages":"269-270"},"PeriodicalIF":0.8,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76812686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We review the main ideas and elements of Interaction-Oriented Software Engineering (IOSE), a program of research that we have pursued for the last two decades, a span of time in which it has grown from philosophy to practical programming abstractions. What distinguishes IOSE from any other program of research is its emphasis on supporting autonomy by modeling the meaning of communication and using that as the basis for engineering decentralized sociotechnical systems. Meaning sounds esoteric but is the basis for practical decision making and a holy grail for the field of distributed systems. We describe our contributions so far, directions for research, and the potential for broad impact on computing.
{"title":"Interaction-Oriented Software Engineering: Programming abstractions for autonomy and decentralization","authors":"A. Chopra","doi":"10.3233/aic-220144","DOIUrl":"https://doi.org/10.3233/aic-220144","url":null,"abstract":"We review the main ideas and elements of Interaction-Oriented Software Engineering (IOSE), a program of research that we have pursued for the last two decades, a span of time in which it has grown from philosophy to practical programming abstractions. What distinguishes IOSE from any other program of research is its emphasis on supporting autonomy by modeling the meaning of communication and using that as the basis for engineering decentralized sociotechnical systems. Meaning sounds esoteric but is the basis for practical decision making and a holy grail for the field of distributed systems. We describe our contributions so far, directions for research, and the potential for broad impact on computing.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"35 1","pages":"381-391"},"PeriodicalIF":0.8,"publicationDate":"2022-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74802406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elizabeth Black, M. Brandão, O. Cocarascu, Bart de Keijzer, Yali Du, Derek Long, Michael Luck, P. McBurney, Albert Meroño-Peñuela, S. Miles, S. Modgil, L. Moreau, M. Polukarov, O. Rodrigues, Carmine Ventre
Current work on multi-agent systems at King’s College London is extensive, though largely based in two research groups within the Department of Informatics: the Distributed Artificial Intelligence (DAI) thematic group and the Reasoning & Planning (RAP) thematic group. DAI combines AI expertise with political and economic theories and data, to explore social and technological contexts of interacting intelligent entities. It develops computational models for analysing social, political and economic phenomena to improve the effectiveness and fairness of policies and regulations, and combines intelligent agent systems, software engineering, norms, trust and reputation, agent-based simulation, communication and provenance of data, knowledge engineering, crowd computing and semantic technologies, and algorithmic game theory and computational social choice, to address problems arising in autonomous systems, financial markets, privacy and security, urban living and health. RAP conducts research in symbolic models for reasoning involving argumentation, knowledge representation, planning, and other related areas, including development of logical models of argumentation-based reasoning and decision-making, and their usage for explainable AI and integration of machine and human reasoning, as well as combining planning and argumentation methodologies for strategic argumentation.
{"title":"Reasoning and interaction for social artificial intelligence","authors":"Elizabeth Black, M. Brandão, O. Cocarascu, Bart de Keijzer, Yali Du, Derek Long, Michael Luck, P. McBurney, Albert Meroño-Peñuela, S. Miles, S. Modgil, L. Moreau, M. Polukarov, O. Rodrigues, Carmine Ventre","doi":"10.3233/aic-220133","DOIUrl":"https://doi.org/10.3233/aic-220133","url":null,"abstract":"Current work on multi-agent systems at King’s College London is extensive, though largely based in two research groups within the Department of Informatics: the Distributed Artificial Intelligence (DAI) thematic group and the Reasoning & Planning (RAP) thematic group. DAI combines AI expertise with political and economic theories and data, to explore social and technological contexts of interacting intelligent entities. It develops computational models for analysing social, political and economic phenomena to improve the effectiveness and fairness of policies and regulations, and combines intelligent agent systems, software engineering, norms, trust and reputation, agent-based simulation, communication and provenance of data, knowledge engineering, crowd computing and semantic technologies, and algorithmic game theory and computational social choice, to address problems arising in autonomous systems, financial markets, privacy and security, urban living and health. RAP conducts research in symbolic models for reasoning involving argumentation, knowledge representation, planning, and other related areas, including development of logical models of argumentation-based reasoning and decision-making, and their usage for explainable AI and integration of machine and human reasoning, as well as combining planning and argumentation methodologies for strategic argumentation.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"91 1","pages":"309-325"},"PeriodicalIF":0.8,"publicationDate":"2022-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72737843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Autonomy and Verification group11 Part of a wider, international, Autonomy and Verification Network of activity: https://autonomy-and-verification.github.io sits within the Department of Computer Science22 https://www.cs.manchester.ac.uk at the University of Manchester. The group has a long history of research into agents and multi-agent systems (both at Manchester and, previously, at the University of Liverpool) particularly in the areas of formal specification and verification, multi-agent programming, ethical agent reasoning, and swarms, teams and organisations.
{"title":"Verifiable autonomy: From theory to applications","authors":"Louise Dennis, C. Dixon, M. Fisher","doi":"10.3233/aic-220115","DOIUrl":"https://doi.org/10.3233/aic-220115","url":null,"abstract":"The Autonomy and Verification group11 Part of a wider, international, Autonomy and Verification Network of activity: https://autonomy-and-verification.github.io sits within the Department of Computer Science22 https://www.cs.manchester.ac.uk at the University of Manchester. The group has a long history of research into agents and multi-agent systems (both at Manchester and, previously, at the University of Liverpool) particularly in the areas of formal specification and verification, multi-agent programming, ethical agent reasoning, and swarms, teams and organisations.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"5 1","pages":"421-431"},"PeriodicalIF":0.8,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84261105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Malleson, M. Birkin, Daniel Birks, Jiaqi Ge, A. Heppenstall, E. Manley, J. McCulloch, Patricia Ternes
Agent-based modelling (ABM) is a facet of wider Multi-Agent Systems (MAS) research that explores the collective behaviour of individual ‘agents’, and the implications that their behaviour and interactions have for wider systemic behaviour. The method has been shown to hold considerable value in exploring and understanding human societies, but is still largely confined to use in academia. This is particularly evident in the field of Urban Analytics; one that is characterised by the use of new forms of data in combination with computational approaches to gain insight into urban processes. In Urban Analytics, ABM is gaining popularity as a valuable method for understanding the low-level interactions that ultimately drive cities, but as yet is rarely used by stakeholders (planners, governments, etc.) to address real policy problems. This paper presents the state-of-the-art in the application of ABM at the interface of MAS and Urban Analytics by a group of ABM researchers who are affiliated with the Urban Analytics programme of the Alan Turing Institute in London (UK). It addresses issues around modelling behaviour, the use of new forms of data, the calibration of models under high uncertainty, real-time modelling, the use of AI techniques, large-scale models, and the implications for modelling policy. The discussion also contextualises current research in wider debates around Data Science, Artificial Intelligence, and MAS more broadly.
{"title":"Agent-based modelling for Urban Analytics: State of the art and challenges","authors":"N. Malleson, M. Birkin, Daniel Birks, Jiaqi Ge, A. Heppenstall, E. Manley, J. McCulloch, Patricia Ternes","doi":"10.3233/AIC-220114","DOIUrl":"https://doi.org/10.3233/AIC-220114","url":null,"abstract":"Agent-based modelling (ABM) is a facet of wider Multi-Agent Systems (MAS) research that explores the collective behaviour of individual ‘agents’, and the implications that their behaviour and interactions have for wider systemic behaviour. The method has been shown to hold considerable value in exploring and understanding human societies, but is still largely confined to use in academia. This is particularly evident in the field of Urban Analytics; one that is characterised by the use of new forms of data in combination with computational approaches to gain insight into urban processes. In Urban Analytics, ABM is gaining popularity as a valuable method for understanding the low-level interactions that ultimately drive cities, but as yet is rarely used by stakeholders (planners, governments, etc.) to address real policy problems. This paper presents the state-of-the-art in the application of ABM at the interface of MAS and Urban Analytics by a group of ABM researchers who are affiliated with the Urban Analytics programme of the Alan Turing Institute in London (UK). It addresses issues around modelling behaviour, the use of new forms of data, the calibration of models under high uncertainty, real-time modelling, the use of AI techniques, large-scale models, and the implications for modelling policy. The discussion also contextualises current research in wider debates around Data Science, Artificial Intelligence, and MAS more broadly.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"64 1","pages":"393-406"},"PeriodicalIF":0.8,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74543864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We are concerned with the construction, formal verification, and safety assurance of dependable multiagent systems. For the case where the system (agents and their environment) can be explicitly modelled, we develop formal verification methods over several logic languages, such as temporal epistemic logic and strategy logic, to reason about the knowledge and strategy of the agents. For the case where the system cannot be explicitly modelled, we study multiagent deep reinforcement learning, aiming to develop efficient and scalable learning methods for cooperative multiagent tasks. In addition to these, we develop (both formal and simulation-based) verification methods for the neural network based perception agent that is trained with supervised learning, considering its safety and robustness against attacks from an adversarial agent, and other approaches (such as explainable AI, reliability assessment, and safety argument) for the analysis and assurance of the learning components. Our ultimate objective is to combine formal methods, machine learning, and reliability engineering to not only develop dependable learning-enabled multiagent systems but also provide rigorous methods for the verification and assurance of such systems.
{"title":"Dependable learning-enabled multiagent systems","authors":"Xiaowei Huang, Bei Peng, Xingyu Zhao","doi":"10.3233/aic-220128","DOIUrl":"https://doi.org/10.3233/aic-220128","url":null,"abstract":"We are concerned with the construction, formal verification, and safety assurance of dependable multiagent systems. For the case where the system (agents and their environment) can be explicitly modelled, we develop formal verification methods over several logic languages, such as temporal epistemic logic and strategy logic, to reason about the knowledge and strategy of the agents. For the case where the system cannot be explicitly modelled, we study multiagent deep reinforcement learning, aiming to develop efficient and scalable learning methods for cooperative multiagent tasks. In addition to these, we develop (both formal and simulation-based) verification methods for the neural network based perception agent that is trained with supervised learning, considering its safety and robustness against attacks from an adversarial agent, and other approaches (such as explainable AI, reliability assessment, and safety argument) for the analysis and assurance of the learning components. Our ultimate objective is to combine formal methods, machine learning, and reliability engineering to not only develop dependable learning-enabled multiagent systems but also provide rigorous methods for the verification and assurance of such systems.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"29 1","pages":"407-420"},"PeriodicalIF":0.8,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78210485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. C. Cardoso, B. Logan, Felipe Meneguzzi, N. Oren, Bruno Yun
Multi-agent systems is an evolving discipline that encompasses many different branches of research. The long-standing Agents at Aberdeen ( A 3 ) group undertakes research across several areas of multi-agent systems, focusing in particular on aspects related to resilience, reliability, and coordination. In this article we introduce the group and highlight past research successes in those themes, building a picture of the strengths within the group. We close the paper outlining the future direction of the group and identify key open challenges and our vision towards solving them.
{"title":"Resilience, reliability, and coordination in autonomous multi-agent systems","authors":"R. C. Cardoso, B. Logan, Felipe Meneguzzi, N. Oren, Bruno Yun","doi":"10.3233/aic-220136","DOIUrl":"https://doi.org/10.3233/aic-220136","url":null,"abstract":"Multi-agent systems is an evolving discipline that encompasses many different branches of research. The long-standing Agents at Aberdeen ( A 3 ) group undertakes research across several areas of multi-agent systems, focusing in particular on aspects related to resilience, reliability, and coordination. In this article we introduce the group and highlight past research successes in those themes, building a picture of the strengths within the group. We close the paper outlining the future direction of the group and identify key open challenges and our vision towards solving them.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"36 1","pages":"339-356"},"PeriodicalIF":0.8,"publicationDate":"2022-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86720930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy
Achieving safe and robust autonomy is the key bottleneck on the path towards broader adoption of autonomous vehicles technology. This motivates going beyond extrinsic metrics such as miles between disengagement, and calls for approaches that embody safety by design. In this paper, we address some aspects of this challenge, with emphasis on issues of motion planning and prediction. We do this through description of novel approaches taken to solving selected sub-problems within an autonomous driving stack, in the process introducing the design philosophy being adopted within Five. This includes safe-by-design planning, interpretable as well as verifiable prediction, and modelling of perception errors to enable effective sim-to-real and real-to-sim transfer within the testing pipeline of a realistic autonomous system.
{"title":"Perspectives on the system-level design of a safe autonomous driving stack","authors":"Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy","doi":"10.3233/aic-220148","DOIUrl":"https://doi.org/10.3233/aic-220148","url":null,"abstract":"Achieving safe and robust autonomy is the key bottleneck on the path towards broader adoption of autonomous vehicles technology. This motivates going beyond extrinsic metrics such as miles between disengagement, and calls for approaches that embody safety by design. In this paper, we address some aspects of this challenge, with emphasis on issues of motion planning and prediction. We do this through description of novel approaches taken to solving selected sub-problems within an autonomous driving stack, in the process introducing the design philosophy being adopted within Five. This includes safe-by-design planning, interpretable as well as verifiable prediction, and modelling of perception errors to enable effective sim-to-real and real-to-sim transfer within the testing pipeline of a realistic autonomous system.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"20 5","pages":""},"PeriodicalIF":0.8,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138495162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho, Filippos Christianos, Mhairi Dunion, Elliot Fosong, Samuel Garcin, Shangmin Guo, Balint Gyevnar, Trevor McInroe, Georgios Papoudakis, Arrasy Rahman, Lukas Schäfer, Massimiliano Tamborski, Giuseppe Vecchio, Cheng Wang, Stefano V. Albrecht
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systemscontrol, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.
{"title":"Deep reinforcement learning for multi-agent interaction","authors":"Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho, Filippos Christianos, Mhairi Dunion, Elliot Fosong, Samuel Garcin, Shangmin Guo, Balint Gyevnar, Trevor McInroe, Georgios Papoudakis, Arrasy Rahman, Lukas Schäfer, Massimiliano Tamborski, Giuseppe Vecchio, Cheng Wang, Stefano V. Albrecht","doi":"10.3233/aic-220116","DOIUrl":"https://doi.org/10.3233/aic-220116","url":null,"abstract":"The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systemscontrol, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observations; and sample-efficient learning based on intrinsic motivation, curriculum learning, causal inference, and representation learning. This article provides a broad overview of the ongoing research portfolio of the group and discusses open problems for future directions.","PeriodicalId":50835,"journal":{"name":"AI Communications","volume":"20 6‐7","pages":""},"PeriodicalIF":0.8,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138495161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：