Abstract
The concept of Synchronism describes circumstances that appear meaningfully related yet nevertheless lack a casual connection. Every day we make use of this concept, from forming new relationships to grooming a new set of skills. Therefore one day in the future we will be able to make use of them for a specific goal. Reinforcement Learning (RL) is a type of learning framework where the solution is presented as a Markov Decision Process (MDP) where the goal is to learn by trial and error, emulating how the human begins to learn. With this type of framework, we can solve very complex non-linear and not deterministic problems. In this novel method, we train the model using a non-deterministic RL and try to find the causal link between those circumstances by observation. This is known as the “Keen Eye” where each circumstance finds a consensus link affecting the outcome using the knowledge from each circumstance involved. We trained agents in two experiments with different domains, the first experiment tries to solve a linear non-deterministic problem, while the second is a non-linear and non-deterministic simulation. With this type of framework, the most common metric is to gather the reward value obtained from the outcome of the experiments, therefore we use this value to measure how performance behaves. Finally, with the results of experiments we discovered that compared with traditional RL, this method can train RL models faster, by obtaining better rewards earlier and makes the RL less susceptible to fall into a local minimum.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Schuler, D.: Social computing - introduction to the special section. Commun. ACM 37(1), 28–29 (1994). https://doi.org/10.1145/175222.175223. https://doi.org/10.1145/175222.175223
Barto, A.G., Sutton, R.S., Brouwer, P.S.: Associative search network: a reinforcement learning associative memory. Biolog. Cybern. 40(3), 201–211 (1981). ISSN: 1432-0770. https://doi.org/10.1007/BF00453370. https://doi.org/10.1007/BF00453370
Bellman, R.: A Markovian decision process. J. Math. Mech. 6(5), 679–684 (1957). http://www.jstor.org/stable/24900506
Bellman, R.E., Dreyfus, S.E.: Functional Approximations and Dynamic Programming. RAND Corporation, Santa Monica (1959)
Bertsekas, D.: Dynamic programming and optimal control 1 (1995)
Shaw, G.L.: Donald Hebb: lhavior. In: Palm, G., Aertsen, A., (eds.), Brain Theory, pp. 231–233. Springer, Berlin (1986). isbn: 978-3-642-70911-1
Jung, C.G.: Synchronicity An Acausal Connecting Principle. Princeton University Press (2012)
Jung, C.G.: Synchronicity An Acausal Connecting Principle. Princeton University Press (1960)
Russell, P.N.S.: Artificial intelligence: a modern approach (2021)
Developing Intelligent Agent Systems: A Practical Guide (2004)
Pomerleau, D.A.: Neural network perception for mobile robot guidance (1993)
Mitchell, T.M.: Machine learning (1997)
Ji, Y., et al.: A survey on tensor techniques and applications in machine learning. IEEE Access 7, 162950–162990 (2019). https://doi.org/10.1109/ACCESS.2019.2949814
Bengio, Y., Goodfellow, I., Courville, A.: Deep learning (2017)
Navarro-Almanza, R., Juáarez-Ramírez, R., Licea, G., Castro, J.R.: Automated ontology extraction from unstructured texts using deep learning (2020)
Beysolow, T.: II. Applied Reinforcement Learning with Python 2019
Rozonoer, L., Mirkin, B., Muchnik, I.: Braverman Readings in Machine Learning. Key Ideas from Inception to Current State (2017)
Biswas, M., Nandy, A.: Reinforcement learning basics (2018)
Bhar, R., Hamori, S.: Hidden Markov models
Stone, P.: Q-learning. In: Sammut, C., Webb, G.I., (eds.), Encyclopedia of Machine Learning and Data Mining, pp. 1033–1033. Springer, Boston, (2017). ISBN: 978-1-4899-7687-1. https://doi.org/10.1007/978-1-4899-7687-1_689. https://doi.org/10.1007/978-1-4899-7687-1_689
Sewak, M.: Deep Reinforcement Learning. Springer, Singapore (2019). https://doi.org/10.1007/978-981-13-8285-7. https://doi.org/10.1007
Justesen, N., et al.: Deep learning for video game playing. IEEE Trans. Games 12(1), 1–20 (2020). https://doi.org/10.1109/TG.2019.2896986
Shao, K., et al.: A Survey of Deep Reinforcement Learning in Video Games (2019). arXiv:1912.10944 [cs.MA]
Schrittwieser, D., Simonyan, J., Silver, K.: Mastering the game of Go without human knowledge. Nature (2017)
Zhang, D., Tian, H., Shan, L., Munir, S., Stankovic, J.A., (eds.), Online Taxicab Demand Model From Big Sensor Data in a Roving Sensor Network (2014)
Jin, J., et al.: An information framework for creating a smart city through internet of things. IEEE Internet Things J. 1(2), 112–121 (2014). https://doi.org/10.1109/JIOT.2013.2296516
Harris, K.: Synchronicity: The Magic. The Mystery, The Meaning (2015)
Williams, R.J., Baird, L.C.: A mathematical analysis of actor-critic architectures for learning optimal controls through incremental dynamic programming. In: Proceedings of the Sixth Yale Workshop on Adaptive and Learning Systems (1990)
Keen/sharp eye. 2021. https://www.merriam-webster.com/dictionary/keen
Walborn, F.: Chapter 3—Carl Jung. In: Walborn, F., (ed.), Religion in Personality Theory, pp. 41–64. Academic, San Diego (2014). ISBN: 978-0-12-407864-2. https://doi.org/10.1016/B978-0-12-407864-2.00003-5. https://www.sciencedirect.com/science/article/pii/B9780124078642000035
Marsala, C., Bouchon-Meunier, B.: Construction of Fuzzy Classes by Fuzzy Partitioning. In: Larsen, H.L., et al., Flexible Query Answering Systems, pp. 497–506. Physica-Verlag HD, Heidelberg. ISBN: 978-3-7908-1834-5
Barto, A.G., Sutton, R.S., Anderso, C.W.: Neuronlike adaptive elements that can solve difficult learning control problem. IEEE Trans. Syst, Man, Cybern (1983)
Packer, C., et al.: Assessing generalization in deep reinforcement learning (2019). arXiv:1810.12282 [cs.LG]
Stephanie, C., Chan, Y., et al.: Measuring the reliability of reinforcement learning algorithms (2020). arXiv: 1912.05663 [stat.ML]
Linse, T., et al.: A convergence study of phase-field models for brittle fracture. Eng. Fract. Mech. 184, 307–318 (2017). ISSN: 0013-7944. https://doi.org/10.1016/j.engfracmech.2017.09.013. https://www.sciencedirect.com/science/article/pii/S0013794417307488
Acknowledgements
This research was supported/partially supported by MyDCI (Maestría y Doctorado en Ciencias e Ingeniería) and CONACYT (Consejo Nacional de Ciencia y Tecnología).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Zamarrón, O., Sanchez, M.A., Rodríguez-Díaz, A. (2022). Synchronisms Using Reinforcement Learning as an Heuristic. In: Castillo, O., Melin, P. (eds) New Perspectives on Hybrid Intelligent System Design based on Fuzzy Logic, Neural Networks and Metaheuristics. Studies in Computational Intelligence, vol 1050. Springer, Cham. https://doi.org/10.1007/978-3-031-08266-5_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-08266-5_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08265-8
Online ISBN: 978-3-031-08266-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)