TY - GEN AB - Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying on Machine Learning (ML), symbolic reasoning, and the ability of their developers for tailoring smart behaviors to specific application domains. However, to forecast the evolution of all possible scenarios is unfeasible. Thus, intelligent agents should autonomously/creatively adapt to the world’s mutability. This paper investigates the meaning of imagination in the context of cognitive agents. In particular, it addresses techniques and approaches to let agents autonomously imagine/simulate their course of action and generate explanations supporting it, and formalizes thematic challenges. Accordingly, we investigate research areas including: (i) reasoning and automatic theorem proving to synthesize novel knowledge via inference; (ii) automatic planning and simulation, used to speculate over alternative courses of action; (iii) machine learning and data mining, exploited to induce new knowledge from experience; and (iv) biochemical coordination, which keeps imagination dynamic by continuously reorganizing it. AD - University of Bologna, Cesena, Italy AD - University of Luxembourg, Esch-sur-Alzette, Luxembourg AD - University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) AD - University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis) AU - Ciatto, Giovanni AU - Najjar, Amro AU - Calbimonte, Jean-Paul AU - Calvaresi, Davide CY - London, UK DA - 2021-05 DO - 10.1007/978-3-030-82017-6_9 DO - DOI ID - 9059 JF - Explainable and Transparent AI and Multi-Agent Systems : Third International Workshop, EXTRAAMAS 2021, Virtual Event, May 3–7, 2021, Revised Selected Papers KW - Informatique KW - multi-agent systems KW - imagination KW - BDI KW - cognitive agents KW - XAI L1 - https://arodes.hes-so.ch/record/9059/files/Author%20postprint.pdf L2 - https://arodes.hes-so.ch/record/9059/files/Author%20postprint.pdf L4 - https://arodes.hes-so.ch/record/9059/files/Author%20postprint.pdf LA - eng LK - https://arodes.hes-so.ch/record/9059/files/Author%20postprint.pdf N2 - Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying on Machine Learning (ML), symbolic reasoning, and the ability of their developers for tailoring smart behaviors to specific application domains. However, to forecast the evolution of all possible scenarios is unfeasible. Thus, intelligent agents should autonomously/creatively adapt to the world’s mutability. This paper investigates the meaning of imagination in the context of cognitive agents. In particular, it addresses techniques and approaches to let agents autonomously imagine/simulate their course of action and generate explanations supporting it, and formalizes thematic challenges. Accordingly, we investigate research areas including: (i) reasoning and automatic theorem proving to synthesize novel knowledge via inference; (ii) automatic planning and simulation, used to speculate over alternative courses of action; (iii) machine learning and data mining, exploited to induce new knowledge from experience; and (iv) biochemical coordination, which keeps imagination dynamic by continuously reorganizing it. PB - 3-7 May 2021 PP - London, UK PY - 2021-05 SN - 978-3-030-82016-9 SN - 0302-9743 T1 - Towards explainable visionary agents :license to dare and imagine TI - Towards explainable visionary agents :license to dare and imagine UR - https://arodes.hes-so.ch/record/9059/files/Author%20postprint.pdf VL - Lecture Notes in Computer Science, vol. 12688 Y1 - 2021-05 ER -