Publications

Found 8 results
Author Title Type [ Year(Asc)]
Filters: Author is Peter Vrancx  [Clear All Filters]
2017
Libin, P., Verstraeten, T., Theys, K., Roijers, D. M., Vrancx, P., & Nowé, A.. (2017). Efficient evaluation of influenza mitigation strategies using preventive bandits. In Sukthankar G., Rodriguez-Aguilar J. (eds) Autonomous Agents and Multiagent Systems. AAMAS 2017. Lecture Notes in Computer Science. Springer.
PDF icon 2017neurocomputing-brys.pdf (1.46 MB)
2016
Verstraeten, T., Vrancx, P., & Nowé, A.. (2016). Fleet Reinforcement Learning Using Dependent Gaussian Processes. In Learning, Inference and Control of Multi-Agent Systems.
PDF icon fleet_rl.pdf (190.58 KB)
Verstraeten, T., Rădulescu, R., Jadoul, Y., Jaspers, T., Conjaerts, R., Brys, T., et al.. (2016). Human Guided Ensemble Learning in StarCraft. 16th Adaptive and Learning Agents Workshop (ALA 2016).
PDF icon paper.pdf (1.01 MB)
2015
Harutyunyan, A., Brys, T., Vrancx, P., & Nowe, A.. (2015). Multi-Scale Reward Shaping via an Off-Policy Ensemble. In International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-15). To appear.
PDF icon ea034-harutyunyan.pdf (219.2 KB)
Harutyunyan, A., Brys, T., Vrancx, P., & Nowe, A.. (2015). Shaping Mario with Human Advice (Demonstration). In International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-15). To appear.
PDF icon de006-harutyunyan.pdf (393.05 KB)