ABSTRACT
Immersive experiences in virtual reality simulations require natural-looking virtual characters. Autonomy researchers argue that only the agent’s own experience can model their behavior. In this regard, the Constitutive Autonomy through Self-programming Hypothesis (CASH) is an effective approach to implement this model. In this paper, we contribute to the discussion of CASH within dynamic and continuous environments by developing mechanisms of memory decay, contradiction penalty, and relative valence. Such improvements aim to see how the agent might continuously reevaluate their learned schemas. The results show that our agents were able to develop autonomously into performing plausible behaviors, despite the changing environment.
- Joshua Achiam and Shankar Sastry. 2017. Surprise-based intrinsic motivation for deep reinforcement learning. arXiv preprint arXiv:1703.01732(2017).Google Scholar
- Michael L. Anderson. 2003. Embodied Cognition: A field guide. Artificial Intelligence 149, 1 (2003), 91–130. https://doi.org/10.1016/S0004-3702(03)00054-7Google ScholarDigital Library
- A. Aubret, L. Matignon, and S. Hassas. 2019. A survey on intrinsic motivation in reinforcement learning. ArXiv abs/1908.06976(2019).Google Scholar
- Helen Bee and Denise Boyd. 2012. The Developing Child. Pearson, New York.Google Scholar
- NP Davies, QH Mehdi, and N Gough. 2006. A framework for implementing deliberative agents in computer games. In Proceedings 20th European Conference on Modeling and Simulation Wolfgang Borutzky, Alessandra Orsoni, Richard Zobel l’ECMS.Google ScholarCross Ref
- Tom Froese, Nathaniel Virgo, and Eduardo Izquierdo. 2007. Autonomy: A Review and a Reappraisal. In Advances in Artificial Life, Fernando Almeida e Costa, Luis Mateus Rocha, Ernesto Costa, Inman Harvey, and António Coutinho(Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 455–464.Google Scholar
- Tom Froese and Tom Ziemke. 2009. Enactive artificial intelligence: Investigating the systemic organization of life and mind. Artificial Intelligence 173, 3 (2009), 466–500. https://doi.org/10.1016/j.artint.2008.12.001Google ScholarDigital Library
- Simon L. Gay, Alain Mille, and Amlie Cordier. 2017. Autonomous object modeling and exploiting: A new approach based on affordances from continual interaction with environment. In 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob). 362–367. https://doi.org/10.1109/DEVLRN.2017.8329831Google ScholarCross Ref
- Olivier L. Georgeon and Amélie Cordier. 2014. Inverting the Interaction Cycle to Model Embodied Agents. Procedia Computer Science 41 (2014), 243–248. https://doi.org/10.1016/j.procs.2014.11.109 5th Annual International Conference on Biologically Inspired Cognitive Architectures, 2014 BICA.Google ScholarCross Ref
- Olivier L. Georgeon, James B. Marshall, and Simon Gay. 2012. Interactional Motivation in artificial systems: Between extrinsic and intrinsic motivation. In 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL). IEEE, 1–2. https://doi.org/10.1109/DevLrn.2012.6400833Google ScholarCross Ref
- Olivier L. Georgeon, James B. Marshall, and Simon Gay. 2012. Interactional Motivation in artificial systems: Between extrinsic and intrinsic motivation. In 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL). 1–2. https://doi.org/10.1109/DevLrn.2012.6400833Google ScholarCross Ref
- Olivier L. Georgeon and Alexander Riegler. 2019. CASH only: Constitutive autonomy through motorsensory self-programming. Cognitive Systems Research 58 (2019), 366–374. https://doi.org/10.1016/j.cogsys.2019.08.006Google ScholarDigital Library
- John Haugeland. 1985. Artificial Intelligence: The Very Idea. Massachusetts Institute of Technology, USA.Google ScholarDigital Library
- Tejas D. Kulkarni, Karthik R. Narasimhan, Ardavan Saeedi, and Joshua B. Tenenbaum. 2016. Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS’16). Curran Associates Inc., Red Hook, NY, USA, 3682–3690.Google Scholar
- Anderson Oliveira Mesquita, Yuri Lenon Barbosa Nogueira, Creto Augusto Vidal, Joaquim Bento Cavalcante-Neto, and Paulo Bruno Sousa Serafim. 2020. Autonomous Foraging with SARSA-based Deep Reinforcement Learning. In Proceedings of the XXII Symposium on Virtual and Augmented Reality (SVR). 1–9. https://doi.org/10.1109/SVR51698.2020.00070Google ScholarCross Ref
- Yuri Nogueira, Carlos Brito, Creto Vidal, and Joaquim Cavalcante-Neto. 2020. Towards intrinsic autonomy through evolutionary computation. Artificial Intelligence Review 53 (08 2020), 4449–4473. https://doi.org/10.1007/s10462-019-09798-1Google ScholarDigital Library
- Jean Piaget. 1952. The origins of intelligence in children.W W Norton & Co, New York.Google Scholar
- Ahmad EL Sallab, Mohammed Abdou, Etienne Perot, and Senthil Yogamani. 2017. Deep reinforcement learning framework for autonomous driving. Electronic Imaging 2017, 19 (2017), 70–76.Google ScholarCross Ref
- A. M. Turing. 1950. I.—Computing Machinery and Intelligence. Mind LIX, 236 (10 1950), 433–460. https://doi.org/10.1093/mind/LIX.236.433Google ScholarCross Ref
- Francisco J. Varela, Eleanor Rosch, and Evan Thompson. 1991. The Embodied Mind: Cognitive Science and Human Experience. The MIT Press. https://doi.org/10.7551/mitpress/6730.001.0001Google ScholarCross Ref
- David Vernon, Robert Lowe, Serge Thill, and Tom Ziemke. 2015. Embodied cognition and circular causality: on the role of constitutive autonomy in the reciprocal coupling of perception and action. Frontiers in Psychology 6 (2015), 1660. https://doi.org/10.3389/fpsyg.2015.01660Google ScholarCross Ref
- Terry Winograd and Fernando Flores. 1987. Understanding Computers and Cognition: A New Foundation for Design. Addison-Wesley Longman Publishing Co., Inc., USA.Google ScholarDigital Library
- Jianyong Xue, Olivier L. Georgeon, and Salima Hassas. 2020. A Constructivist Approach and Tool for Autonomous Agent Bottom-up Sequential Learning. International Journal of Educational and Pedagogical Sciences 14, 10(2020), 886 – 894. https://publications.waset.org/vol/166Google Scholar
Index Terms
- Autonomous Foraging of Virtual Characters with a Constructivist Cognitive Architecture
Recommendations
A hybrid agent architecture for modeling autonomous agents in SAGE
IDEAL'05: Proceedings of the 6th international conference on Intelligent Data Engineering and Automated LearningThis paper highlights the Hybrid agent construction model being developed that allows the description and development of autonomous agents in SAGE (Scalable, fault Tolerant Agent Grooming Environment) – a second generation FIPA-Compliant Multi-Agent ...
CASH only: Constitutive autonomy through motorsensory self-programming
AbstractConstitutive autonomy is the capacity of an entity to perpetually develop its individual constitution and coupling with its environment. We argue that computational entities (i.e., entities that can perform computation) can gain ...
Autonomous Learning Agents: Layered Learning and Ad Hoc Teamwork
AAMAS '16: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent SystemsIn order to achieve long-term autonomy in the real world, fully autonomous agents need to be able to learn, both to improve their behaviors in a complex, dynamically changing world, and to enable interaction with previously unfamiliar agents. This talk ...
Comments