JIM MARTIN CATACORA OCANA

PhD Student

PhD program:: XXXIV
email: catacora@diag.uniroma1.it
building: Department of Computer, Control, and Management Engineering, via Ariosto 25, Rome
room: B121

supervisor: Daniele Nardi

I am interested in general methods for the autonomous development of highly intelligent agents, such as: deep reinforcement learning and evolutionary computation. Currently, my focus in on designing improved reinforcement learning algorithms for handling sparse reward environments.

Research products

11573/1382008 - 2019 - Cooperative Multi-agent Deep Reinforcement Learning in a 2 Versus 2 Free-Kick Task

Catacora Ocana, J. M.; Riccio, F.; Capobianco, R.; Nardi, D. - 04b Atto di convegno in volume

conference: 23rd Annual RoboCup International Symposium, RoboCup 2019 (Sydney; Australia)

book: RoboCup 2019: Robot World Cup XXIII - (978-3-030-35698-9; 978-3-030-35699-6)

11573/1381509 - 2019 - Cooperative multi-agent deep reinforcement learning in soccer domains

Catacora Ocana, Jim Martin; Capobianco, R.; Riccio, F.; Nardi, D. - 04b Atto di convegno in volume

conference: 18th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2019 (Montreal; Canada)

book: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS - ()