David Simões

Subject	Learning Coordination in Multi-Agent Systems
Advisor	Nuno Lau, Luis Paulo Reis
Group	Intelligent Robotics and Systems
Status	PhD student
Starts	2015/10/01
Ends	2020/05/31
Country	Portugal
Projects
Past projects
Events	EPIA'2017, Robot'2017
Proposals
Personal page

Linked-In [1]

Google Scholar Profile [2]

ORCID [3]

Publications

Articles in international journals listed in the ISI

• David Simões, Nuno Lau, Luis Paulo Reis. Multi-agent actor centralized-critic with communication. Neurocomputing, January 2020 [IF 2018: 4.072 (Q1, 28/134)]
• Abbas Abdolmaleki, David Simões, Nuno Lau, Luis Paulo Reis, Gerhard Neumann. Contextual Direct Policy Search: With Regularized Covariance Matrix Estimation. Journal of Intelligent & Robotic Systems, vol. 96, no. 2, p. 141-157, November 2019 [IF 2018: 2.020 (Q3, 17/26)]
• Marisa Lousada, Luis M. T. Jesus, Sylvie Capelas, Cláudia Margaça, David Simões, Ana Rita Valente, Andreia Hall, Victoria Joffe. Phonological and Articulation Treatment Approaches in Portuguese Children With Speech and Language Impairments: A Randomized Controlled Intervention Study. International Journal of Language & Communication Disorders, vol. 48, no. 2, p. 172-187, March 2013 [IF 2013: 1.392]

Articles in conference proceedings

• David Simões, Pedro Amaro, Tiago Silva, Nuno Lau, Luis Paulo Reis. Learning Low-Level Behaviors and High-Level Strategies in Humanoid Soccer. Robot 2019: Fourth Iberian Robotics Conference, vol. Advances in Intelligent Systems and Computing, vol 1093, p. 537-548, 2020
• David Simões, Nuno Lau, Luis Paulo Reis. Adjusted Bounded Weighted Policy Learner. RoboCup 2018: Robot World Cup XXII, Montreal, vol. LNCS 11374, Springer, p. 324-336, 2019
• David Simões, Nuno Lau, Luis Paulo Reis. Multi-Agent Deep Reinforcement Learning with Emergent Communication. IJCNN 2019 - International Joint Conference on Neural NetworksProceedings, Budapest, Hungary, July 2019
• David Simões, Nuno Lau, Luis Paulo Reis. Multi-agent Neural Reinforcement-Learning System with Communication. WorldCIST'19 - New Knowledge in Information Systems and Technologies, La Toja, Spain, vol. Springer AISC 931, p. 3-12, April 2019
• David Simões, Nuno Lau, Luis Paulo Reis. Guided Deep Reinforcement Learning in the GeoFriends2 Environment. IJCNN 2018 : International Joint Conference on Neural Networks, Rio de Janeiro, Brazil, July 2018
• Abbas Abdolmaleki, David Simões, Nuno Lau, Luis Paulo Reis, Bob Price, Gerhard Neumann. Stochastic Search In Changing Situations. The AAAI-17 Workshop on Human-Machine Collaborative Learning, p. 636-642, 2017
• Mohammadreza Kasaei, David Simões, Nuno Lau, Artur Pereira. A Hybrid ZMP-CPG BasedWalk Engine for Biped Robots. Robot2017: Third Iberian Robotics Conference, p. 1560-1571, November 2017
• David Simões, Nuno Lau, Luis Paulo Reis. Mixed-Policy Asynchronous Deep Q-Learning. Robot2017: Third Iberian Robotics Conference, Seville, Spain, p. 976-987, November 2017
• David Simões, Nuno Lau, Luis Paulo Reis. Multi-agent Double Deep Q-Networks. Progress in Artificial Intelligence 18th EPIA Conference on Artificial Intelligence, EPIA 2017 Porto, Portugal, September 5–8, 2017 Proceedings, Porto, Portugal, vol. LNCS 10423, p. 123-134, September 2017
• David Simões, Rui Brás, Nuno Lau, Artur Pereira. A coordinated team of agents to solve mazes. Advances in Intelligent Systems and Computing, vol. 418, p. pp. 381-392, 2016
• Abbas Abdolmaleki, David Simões, Nuno Lau, Luis Paulo Reis. Learning a Humanoid Kick With Controlled Distance. RoboCup 2016: Robot World Cup XX, July 2016

PhD thesis

• David Simões. Learning Coordination in Multi-Agent Systems. PhD Thesis, Universidade de Aveiro, May 2020