Francisco S. Melo
Francisco S. Melo
INESC-ID/Instituto Superior Técnico
Verified email at inesc-id.pt - Homepage
TitleCited byYear
An analysis of reinforcement learning with function approximation
FS Melo, SP Meyn, MI Ribeiro
Proceedings of the 25th international conference on Machine learning, 664-671, 2008
1412008
Active learning for reward estimation in inverse reinforcement learning
M Lopes, F Melo, L Montesano
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2009
1312009
Affordance-based imitation learning in robots
M Lopes, FS Melo, L Montesano
2007 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2007
1252007
Decentralized MDPs with sparse interactions
FS Melo, M Veloso
Artificial Intelligence 175 (11), 1757-1789, 2011
902011
Interaction-driven Markov games for decentralized multiagent planning under uncertainty
MTJ Spaan, FS Melo
Proceedings of the 7th international joint conference on Autonomous agents …, 2008
822008
Learning of coordination: Exploiting sparse interactions in multiagent systems
FS Melo, M Veloso
Proceedings of The 8th International Conference on Autonomous Agents and …, 2009
752009
Q-learning with linear function approximation
FS Melo, MI Ribeiro
International Conference on Computational Learning Theory, 308-322, 2007
482007
Abstraction levels for robotic imitation: Overview and computational approaches
M Lopes, F Melo, L Montesano, J Santos-Victor
From Motor Learning to Interaction Learning in Robots, 313-355, 2010
472010
A computational model of social-learning mechanisms
M Lopes, FS Melo, B Kenward, J Santos-Victor
Adaptive Behavior 17 (6), 467-483, 2009
372009
Emotion-based intrinsic motivation for reinforcement learning agents
P Sequeira, FS Melo, A Paiva
International Conference on Affective Computing and Intelligent Interaction …, 2011
362011
Personalized assistance for dressing users
SD Klee, BQ Ferreira, R Silva, JP Costeira, FS Melo, M Veloso
International Conference on Social Robotics, 359-369, 2015
312015
Learning from demonstration using MDP induced metrics
FS Melo, M Lopes
European Conference on Machine Learning and Principles and Practice of …, 2010
272010
Learning by appraising: an emotion-based approach to intrinsic reward design
P Sequeira, FS Melo, A Paiva
Adaptive Behavior 22 (5), 330-349, 2014
232014
Fitted natural actor-critic: A new algorithm for continuous state-action MDPs
FS Melo, M Lopes
European Conference on Machine Learning and Principles and Practive of …, 2008
222008
Just follow the suit! trust in human-robot interactions during card game playing
F Correia, P Alves-Oliveira, N Maia, T Ribeiro, S Petisca, FS Melo, ...
2016 25th IEEE international symposium on robot and human interactive …, 2016
182016
The geometry friends game AI competition
R Prada, P Lopes, J Catarino, J Quitério, FS Melo
2015 IEEE Conference on Computational Intelligence and Games (CIG), 431-438, 2015
182015
A flexible approach to modeling unpredictable events in MDPs
S Witwicki, FS Melo, J Capitan, MTJ Spaan
23rd International Conference on Automated Planning and Scheduling, 2013
172013
Coordinated learning in multiagent MDPs with infinite state-space
FS Melo, MI Ribeiro
Autonomous Agents and Multi-Agent Systems 21 (3), 321-367, 2010
172010
A unified framework for imitation-like behaviors
F Melo, M Lopes, J Santos-Victor, MI Ribeiro
4th International Symposium in Imitation in Animals and Artifacts, Newcastle, UK, 2007
172007
Transition entropy in partially observable Markov decision processes.
FS Melo, MI Ribeiro
IAS, 282-289, 2006
172006
The system can't perform the operation now. Try again later.
Articles 1–20