Abstract
Recent innovations in Deep Reinforcement Learning (DRL) and Artificial Intelligence (AI) techniques have allowed for the development of artificial agents that can outperform human counterparts. But when it comes to multiagent task contexts, the behavioral patterning of AI agents is just as important as their performance. Indeed, successful multi-agent interaction requires that co-actors behave reciprocally, anticipate each other’s behaviors, and readily perceive each other’s behavioral intentions. Thus, developing AI agents that can produce behaviors compatible with human co-actors is of vital importance. Of particular relevance here, research exploring the dynamics of human behavior has demonstrated that many human behaviors and actions can be modeled using a small set of dynamical perceptual-motor primitives (DPMPs) and, moreover, that these primitives can also capture the complex behavior of humans in multiagent scenarios. Motived by this understanding, the current paper proposes methodologies which use DPMPs to augment the training and action dynamics of DRL agents to ensure that the agents inherit the essential pattering of human behavior while still allowing for optimal exploration of the task solution space during training. The feasibility of these methodologies is demonstrated by creating hybrid DPMP-DRL agents for a multiagent herding task. Overall, this approach leads to faster training of DRL agents while also exhibiting behavior characteristics of expert human actors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv arXiv:1912.06680 (2019)
Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350–354 (2019)
Pohlen, T., et al.: Observe and look further: achieving consistent performance on Atari. arXiv arXiv:1805.11593 (2018)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)
Shek, J.: Takeaways from OpenAI Five [AI/ML, Dota Summary] (2019). https://senrigan.io/blog/takeaways-from-openai-5/
Carroll, M., et al.: On the utility of learning about humans for human-AI coordination. In: Advances in Neural Information Processing Systems, NeurIPS 2019, vol. 32 (2019)
Nalepka, P., et al.: Interaction flexibility in artificial agents teaming with humans. In: CogSci 2021 (2021). https://escholarship.org/uc/item/9ks6n70q
Bain, M., Sammut, C.: A framework for behavioural cloning. In: Machine Intelligence 15. Intelligent Agents, pp. 103–129. Oxford University, GBR (1999). St. Catherine’s College, Oxford, July 1995
Ho, J., Ermon, S.: Generative adversarial imitation learning. arXiv arXiv:1606.03476 (2016)
Maclin, R., et al.: Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression. In: AAAI (2005)
Amodei, D., et al.: Concrete problems in AI safety. arXiv arXiv:1606.06565 (2016)
Osa, T., et al.: An algorithmic perspective on imitation learning. Found. Trends Robot. 7, 1–179 (2018)
Patil, G., et al.: Hopf bifurcations in complex multiagent activity: the signature of discrete to rhythmic behavioral transitions. Brain Sci. 10, 536 (2020)
Nalepka, P., et al.: Human social motor solutions for human–machine interaction in dynamical task contexts. Proc. Natl. Acad. Sci. U. S. A. 116, 1437–1446 (2019)
Richardson, M.J., et al.: Modeling embedded interpersonal and multiagent coordination. In: Proceedings of the 1st International Conference on Complex Information Systems, pp. 155–164. SCITEPRESS - Science and Technology Publications (2016)
Warren, W.H.: The dynamics of perception and action. Psychol. Rev. 113, 358–389 (2006)
Kelso, J.A.S.: Dynamic Patterns: The Self-Organization of Brain and Behavior. MIT Press, Cambridge (1997)
Schmidt, R.C., Richardson, M.J.: Dynamics of interpersonal coordination. In: Fuchs, A., Jirsa, V.K. (eds.) Coordination: Neural, Behavioral and Social Dynamics, pp. 281–308. Springer , Heidelberg (2008). https://doi.org/10.1007/978-3-540-74479-5_14
Nalepka, P., et al.: Herd those sheep: emergent multiagent coordination and behavioral-mode switching. Psychol. Sci. 28, 630–650 (2017)
Sternad, D., et al.: Bouncing a ball: tuning into dynamic stability. J. Exp. Psychol. Hum. Percept. Perform. 27, 1163–1184 (2001)
Fajen, B.R., et al.: A dynamical model of visually-guided steering, obstacle avoidance, and route selection. Int. J. Comput. Vis. 54, 13–34 (2003). https://doi.org/10.1023/A:1023701300169
Lamb, M., et al.: To pass or not to pass: modeling the movement and affordance dynamics of a pick and place task. Front. Psychol. 8, 1061 (2017)
Ijspeert, A.J., et al.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25, 328–373 (2013). https://doi.org/10.1162/NECO_a_00393
Hogan, N., Sternad, D.: On rhythmic and discrete movements: reflections, definitions and implications for motor control. Exp. Brain Res. 181(1), 13–30 (2007). https://doi.org/10.1007/s00221-007-0899-y
Kay, B.A., et al.: Space-time behavior of single and bimanual rhythmical movements: data and limit cycle model. J. Exp. Psychol. Hum. Percept. Perform. 13, 178–192 (1987)
Vesper, C., et al.: Joint action: mental representations, shared information and general mechanisms for coordinating with others. Front. Psychol. 07, 2039 (2017)
Repp, B.H., Keller, P.E.: Adaptation to tempo changes in sensorimotor synchronization: effects of intention, attention, and awareness. Q. J. Exp. Psychol. Sect. A Hum. Exp. Psychol. 57, 499–521 (2004)
Lagarde, J.: Challenges for the understanding of the dynamics of social coordination. Front. Neurorobot. 7, 18 (2013)
Richardson, M.J., et al.: Challenging the egocentric view of coordinated perceiving, acting, and knowing. In: Mind Context, pp. 307–333 (2010)
Schmidt, R.C., O’Brien, B.: Evaluating the dynamics of unintended interpersonal coordination. Ecol. Psychol. 9, 189–206 (1997)
Lamb, M., et al.: A hierarchical behavioral dynamic approach for naturally adaptive human-agent pick-and-place interactions. Complexity, 2019 , 16 (2019). John Wiley & Sons, Inc., USA. https://doi.org/10.1155/2019/5964632
Yokoyama, K., Yamamoto, Y.: Three people can synchronize as coupled oscillators during sports activities. PLoS Comput. Biol. 7, e1002181 (2011)
Zhang, M., et al.: Critical diversity: divided or United States of social coordination. PLoS ONE 13, e0193843 (2018)
Schaal, S., Peters, J., Nakanishi, J., Ijspeert, A.: Learning movement primitives. In: Dario, P., Chatila, R. (eds.) Robotics Research. The Eleventh International Symposium. STAR, vol. 15, pp. 561–572. Springer, Heidelberg (2005). https://doi.org/10.1007/11008941_60
Schaal, S., et al.: Nonlinear dynamical systems as movement primitives. In: International Conference on Humanoid Robots, Cambridge, MA, vol. 38, pp. 117–124 (2001)
Ijspeert, A.J., et al.: Movement imitation with nonlinear dynamical systems in humanoid robots. In: Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292), vol. 2, pp. 1–6 (2002)
Mukovskiy, A., et al.: Modeling of coordinated human body motion by learning of structured dynamic representations. In: Laumond, J.-P., Mansard, N., Lasserre, J.-B. (eds.) Geometric and Numerical Foundations of Movements. STAR, vol. 117, pp. 237–267. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-51547-2_11
Nalepka, P., et al.: “Human-like” emergent behavior in an evolved agent for a cooperative shepherding task. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017), Vancouver, Canada (2017)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2017)
Arulkumaran, K., et al.: Deep reinforcement learning: a brief survey. IEEE Sig. Process. Mag. 34, 26–38 (2017)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Machine Learning (2016)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings. International Conference on Learning Representations, ICLR (2016)
Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12, e0172395 (2017)
Hester, T., et al.: Learning from demonstrations for real world reinforcement learning. arXiv arXiv:1704.03732 (2017)
Hussein, A., et al.: Imitation learning: a survey of learning methods. ACM Comput. Surv. 50, 1–35 (2017)
Nalepka, P., Kallen, R.W., Chemero, A., Saltzman, E., Richardson, M.J.: Practical applications of multiagent shepherding for human-machine interaction. In: Demazeau, Y., Matson, E., Corchado, J.M., De la Prieta, F. (eds.) PAAMS 2019. LNCS (LNAI), vol. 11523, pp. 168–179. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-24209-1_14
Auletta, F., et al.: Herding stochastic autonomous agents via local control rules and online global target selection strategies. arXiv arXiv:2010.00386 (2020)
Auletta, F., et al.: Human-inspired strategies to solve complexjoint tasks in multi agent systems (2021)
Rigoli, L.M., et al.: Employing models of human social motor behavior for artificial agent trainers. In: An, B., et al. (eds.) Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020), p. 9. International Foundation for Autonomous Agents and Multiagent Systems, Auckland (2020)
Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv (2018)
Acknowledgments
This work was supported by ARC Future Fellowship (Richardson, FT180 100447), Macquarie University Research Fellowship (Nalepka), and Human Performance Research Network (HPRnet, partnership grant ID9024).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Patil, G., Nalepka, P., Rigoli, L., Kallen, R.W., Richardson, M.J. (2021). Dynamical Perceptual-Motor Primitives for Better Deep Reinforcement Learning Agents. In: Dignum, F., Corchado, J.M., De La Prieta, F. (eds) Advances in Practical Applications of Agents, Multi-Agent Systems, and Social Good. The PAAMS Collection. PAAMS 2021. Lecture Notes in Computer Science(), vol 12946. Springer, Cham. https://doi.org/10.1007/978-3-030-85739-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-85739-4_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85738-7
Online ISBN: 978-3-030-85739-4
eBook Packages: Computer ScienceComputer Science (R0)