Abstract
We consider the problem of optimizing a controller for agents whose observation and action spaces are continuous, i.e., where the controller is a multivariate real function \(f: \mathbb {R}^n \rightarrow \mathbb {R}^m\). We use genetic programming (GP) for solving this optimization problem. Namely, we employ a multi-tree-based GP variant, where a candidate solution is an array of m trees, each encoding a univariate function of the agent observation. We compare this form of optimization against the more common one where the controller is a multi-layer perceptron, with a predefined topology, whose weights are optimized through (neuro)evolution (NE). Moreover, we consider an evolutionary algorithm, GraphEA, that directly evolves graphs, each having n input nodes and m output nodes. We apply these three approaches to the case of simulated modular soft robots , where a robot is an aggregation of identical soft modules, each employing a controller that processes the local observation and produces the local action. We find that, in our scenario, multi-tree-based GP is competitive with NE and tends to produce different behaviors. We then experimentally investigate the possibility of optimizing a controller using another, pre-optimized one, as teacher, i.e., we realize a form of offline imitation learning . We consider all the teacher-learner pairs resulting from the three evolutionary algorithms and find that NE is a better learner than GP and GraphEA. However, controllers obtained through offline imitation learning are far less effective than those obtained through direct evolution. We hypothesize that this gap in effectiveness may be explained by the possibility, given by direct evolution, of exploring during the simulations a larger portion of the observation-action space.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bacardit, J., Brownlee, A.E., Cagnoni, S., Iacca, G., McCall, J., Walker, D.: The intersection of evolutionary computation and explainable AI. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 1757–1762 (2022)
Bartoli, A., De Lorenzo, A., Medvet, E., Squillero, G.: Multi-level diversity promotion strategies for grammar-guided genetic programming. Appl. Soft Comput. 83, 105599 (2019)
Ferigo, A., Iacca, G., Medvet, E., Pigozzi, F.: Evolving Hebbian learning rules in voxel-based soft robots. IEEE Trans. Cogn. Dev. Syst. (2022)
Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1, 47–62 (2008)
Françoso Dal Piccol Sotto, L., Kaufmann, P., Atkinson, T., Kalkreuth, R., Porto Basgalupp, M.: Graph representations in genetic programming. Genet. Program. Evolvable Mach. 22(4), 607–636 (2021)
Harding, S., Miller, J.F.: Evolution of robot controller using cartesian genetic programming. In: Genetic Programming: 8th European Conference, EuroGP 2005, Lausanne, Switzerland, March 30-April 1, 2005. Proceedings 8, pp. 62–73. Springer (2005)
Hiller, J., Lipson, H.: Automatic design and manufacture of soft robots. IEEE Trans. Robot. 28(2), 457–466 (2012)
Jin, L., Li, S., Yu, J., He, J.: Robot manipulator control using neural networks: a survey. Neurocomputing 285, 23–34 (2018)
Kadlic, B., Sekaj, I., Perneckỳ, D.: Design of continuous-time controllers using cartesian genetic programming. IFAC Proc. Vol. 47(3), 6982–6987 (2014)
Koza, J.R., Rice, J.P.: Automatic programming of robots using genetic programming. In: AAAI, vol. 92, pp. 194–207 (1992)
La Cava, W., Orzechowski, P., Burlacu, B., de França, F.O., Virgolin, M., Jin, Y., Kommenda, M., Moore, J.H.: Contemporary symbolic regression methods and their relative performance (2021). arXiv:2107.14351
Legrand, J., Terryn, S., Roels, E., Vanderborght, B.: Reconfigurable, multi-material, voxel-based soft robots. IEEE Robot. Autom. Lett. (2023)
Lewis, M.A., Fagg, A.H., Solidum, A., et al.: Genetic programming approach to the construction of a neural network for control of a walking robot. In: ICRA, pp. 2618–2623. Citeseer (1992)
Lobov, S.A., Zharinov, A.I., Makarov, V.A., Kazantsev, V.B.: Spatial memory in a spiking neural network with robot embodiment. Sens. 21(8), 2678 (2021)
Medvet, E., Bartoli, A.: Evolutionary optimization of graphs with graphea. In: International Conference of the Italian Association for Artificial Intelligence, pp. 83–98. Springer (2021)
Medvet, E., Bartoli, A., De Lorenzo, A., Fidel, G.: Evolution of distributed neural controllers for voxel-based soft robots. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, pp. 112–120 (2020a)
Medvet, E., Bartoli, A., De Lorenzo, A., Seriani, S.: 2D-VSR-Sim: a simulation tool for the optimization of 2-D voxel-based soft robots. SoftwareX 12, 100573 (2020)
Medvet, E., Nadizar, G., Manzoni, L.: JGEA: a modular java framework for experimenting with evolutionary computation. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 2009–2018 (2022a)
Medvet, E., Nadizar, G., Pigozzi, F.: On the impact of body material properties on neuroevolution for embodied agents: the case of voxel-based soft robots. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 2122–2130 (2022b)
Medvet, E., Pozzi, S., Manzoni, L.: A general purpose representation and adaptive EA for evolving graphs. In: Proceedings of the Genetic and Evolutionary Computation Conference (2023)
Mei, Y., Chen, Q., Lensen, A., Xue, B., Zhang, M.: Explainable artificial intelligence by genetic programming: a survey. IEEE Trans. Evol. Comput. (2022)
Miller, J.F., Harding, S.L.: Cartesian genetic programming. In: Proceedings of the 10th Annual Conference Companion on Genetic and Evolutionary Computation, pp. 2701–2726 (2008)
Nadizar, G., Medvet, E., Miras, K.: On the schedule for morphological development of evolved modular soft robots. In: European Conference on Genetic Programming (Part of EvoStar), pp. 146–161. Springer (2022a)
Nadizar, G., Medvet, E., Nichele, S., Pontes-Filho, S.: An experimental comparison of evolved neural network models for controlling simulated modular soft robots. Appl. Soft Comput. 110610 (2023a)
Nadizar, G., Medvet, E., Ramstad, H.H., Nichele, S., Pellegrino, F.A., Zullich, M.: Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots. Knowl. Eng. Rev. 37 (2022b)
Nadizar, G., Medvet, E., Walker, K., Risi, S.: A fully-distributed shape-aware neural controller for modular robots. In: Proceedings of the Genetic and Evolutionary Computation Conference (2023b)
Nolfi, S.: Behavioral and Cognitive Robotics: an Adaptive Perspective. Stefano Nolfi (2021)
Nordin, P., Banzhaf, W.: Genetic programming controlling a miniature robot. In: Working Notes for the AAAI Symposium on Genetic Programming, vol. 61, p. 67. MIT, Cambridge, MA, USA, AAAI (1995)
Pfeifer, R., Bongard, J.: How the body shapes the way we think: a new view of intelligence. MIT press (2006)
Pigozzi, F., Tang, Y., Medvet, E., Ha, D.: Evolving modular soft robots without explicit inter-module communication using local self-attention. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 148–157 (2022)
Poli, R., Langdon, W.B., McPhee, N.F.: A field guide to genetic programming (2008)
Salvato, E., Fenu, G., Medvet, E., Pellegrino, F.A.: Crossing the reality gap: a survey on sim-to-real transferability of robot controllers in reinforcement learning. IEEE Access (2021)
Seo, K., Hyun, S.: Toward automatic gait generation for quadruped robots using cartesian genetic programming. In: Applications of Evolutionary Computation: 16th European Conference, EvoApplications 2013, Vienna, Austria, April 3–5, 2013. Proceedings 16, pp. 599–605. Springer (2013)
Squillero, G., Tonda, A.: Divergence of character and premature convergence: a survey of methodologies for promoting diversity in evolutionary optimization. Inf. Sci. 329, 782–799 (2016)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
Sui, X., Cai, H., Bie, D., Zhang, Y., Zhao, J., Zhu, Y.: Automatic generation of locomotion patterns for soft modular reconfigurable robots. Appl. Sci. 10(1), 294 (2020)
Talamini, J., Medvet, E., Bartoli, A., De Lorenzo, A.: Evolutionary synthesis of sensing controllers for voxel-based soft robots. In: ALIFE 2019: The 2019 Conference on Artificial Life, pp. 574–581. MIT Press (2019)
Turner, A.J., Miller, J.F.: Recurrent cartesian genetic programming. In: Parallel Problem Solving from Nature–PPSN XIII: 13th International Conference, Ljubljana, Slovenia, September 13–17, 2014. Proceedings 13, pp. 476–486. Springer (2014)
Virgolin, M., Alderliesten, T., Witteveen, C., Bosman, P.A.: Improving model-based genetic programming for symbolic regression of small expressions. Evol. Comput. 29(2), 211–237 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Medvet, E., Nadizar, G. (2024). GP for Continuous Control: Teacher or Learner? The Case of Simulated Modular Soft Robots. In: Winkler, S., Trujillo, L., Ofria, C., Hu, T. (eds) Genetic Programming Theory and Practice XX. Genetic and Evolutionary Computation. Springer, Singapore. https://doi.org/10.1007/978-981-99-8413-8_11
Download citation
DOI: https://doi.org/10.1007/978-981-99-8413-8_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8412-1
Online ISBN: 978-981-99-8413-8
eBook Packages: Computer ScienceComputer Science (R0)