Peter Vrancx - RankMe

71 papers A* 5A 9B 5C 3Misc 1Journal 27Unranked 18

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	Depth Scaling in Graph Neural Networks: Understanding the Flat Curve Behavior. Trans. Mach. Learn. Res. Diana Gomes, Kyriakos Efthymiadis, Ann Nowé, Peter Vrancx
2024	—	`conf`	Understanding Feature/Structure Interplay in Graph Neural Networks. LoG Diana Gomes, Ann Nowé, Peter Vrancx
2023	B	`conf`	AMPeD: An Analytical Model for Performance in Distributed Training of Transformers. ISPASS Diksha Moolchandani, Joyjit Kundu, Frederik Ruelens, Peter Vrancx, Timon Evenblij, Manu Perumkunnil
2023	—	`conf`	Quantized Dynamics Models for Hardware-Efficient Control and Planning in Model-Based RL. PKDD/ECML Workshops (5) Nitish Satya Murthy, Francky Catthoor, Marian Verhelst, Peter Vrancx
2022	—	`conf`	DIANA: An End-to-End Energy-Efficient Digital and ANAlog Hybrid Neural Network SoC. ISSCC Kodai Ueyoshi, Ioannis A. Papistas, Pouya Houshmand, Giuseppe Maria Sarda, Vikram Jain, Man Shi, Qilin Zheng, Juan Sebastian Piedrahita Giraldo, Peter Vrancx, Jonas Doevenspeck, Debjyoti Bhattacharjee, Stefan Cosemans, Arindam Mallik, Peter Debacker, Diederik Verkest, Marian Verhelst
2022	J	`jnl`	Dynamic Quantization Range Control for Analog-in-Memory Neural Networks Acceleration. ACM Trans. Design Autom. Electr. Syst. Nathan Laubeuf, Jonas Doevenspeck, Ioannis A. Papistas, Michele Caselli, Stefan Cosemans, Peter Vrancx, Debjyoti Bhattacharjee, Arindam Mallik, Peter Debacker, Diederik Verkest, Francky Catthoor, Rudy Lauwereins
2022	Misc	`conf`	Learn to Learn on Chip: Hardware-aware Meta-learning for Quantized Few-shot Learning at the Edge. SEC Nitish Satya Murthy, Peter Vrancx, Nathan Laubeuf, Peter Debacker, Francky Catthoor, Marian Verhelst
2021	J	`jnl`	Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow. CoRR John McLeod, Hrvoje Stojic, Vincent Adam, Dongho Kim, Jordi Grau-Moya, Peter Vrancx, Felix Leibfried
2021	B	`conf`	Noise tolerant ternary weight deep neural networks for analog in-memory inference. IJCNN Jonas Doevenspeck, Peter Vrancx, Nathan Laubeuf, Arindam Mallik, Peter Debacker, Diederik Verkest, Rudy Lauwereins, Wim Dehaene
2020	A*	`conf`	Batch Reinforcement Learning with Hyperparameter Gradients. ICML Byung-Jun Lee, Jongmin Lee, Peter Vrancx, Dongho Kim, Kee-Eung Kim
2019	J	`jnl`	Compatible features for Monotonic Policy Improvement. CoRR Marcin B. Tomczak, Sergio Valcarcel Macua, Enrique Munoz de Cote, Peter Vrancx
2019	J	`jnl`	Disentangled Skill Embeddings for Reinforcement Learning. CoRR Janith C. Petangoda, Sergio Pascual-Diaz, Vincent Adam, Peter Vrancx, Jordi Grau-Moya
2019	A*	`conf`	Per-Decision Option Discounting. ICML Anna Harutyunyan, Peter Vrancx, Philippe Hamel, Ann Nowé, Doina Precup
2019	J	`jnl`	Policy Optimization Through Approximated Importance Sampling. CoRR Marcin B. Tomczak, Dongho Kim, Peter Vrancx, Kee-Eung Kim
2019	—	`conf`	Soft Q-Learning with Mutual-Information Regularization. ICLR (Poster) Jordi Grau-Moya, Felix Leibfried, Peter Vrancx
2018	J	`jnl`	Convolutional Neural Networks for Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control. IEEE Trans. Smart Grid Bert J. Claessens, Peter Vrancx, Frederik Ruelens
2018	J	`jnl`	Learning High-level Representations from Demonstrations. CoRR Garrett Andersen, Peter Vrancx, Haitham Bou-Ammar
2018	A*	`conf`	Learning With Options That Terminate Off-Policy. AAAI Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon, Doina Precup, Ann Nowé
2018	J	`jnl`	Model-Based Stabilisation of Deep Reinforcement Learning. CoRR Felix Leibfried, Rasul Tutunov, Peter Vrancx, Haitham Bou-Ammar
2018	A*	`conf`	Reinforcement Learning in POMDPs With Memoryless Options and Option-Observation Initiation Sets. AAAI Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan, Peter Vrancx, Hélène Plisnier, Ann Nowé
2018	J	`jnl`	Reports on the 2018 AAAI Spring Symposium Series. AI Mag. Christopher Amato, Haitham Bou-Ammar, Elizabeth F. Churchill, Erez Karpas, Takashi Kido, Mike Kuniavsky, William F. Lawless, Francesca Rossi, Frans A. Oliehoek, Stephen Russell, Keiki Takadama, Siddharth Srivastava, Karl Tuyls, Philip van Allen, K. Brent Venable, Peter Vrancx, Shiqi Zhang
2017	A	`conf`	Analysing Congestion Problems in Multi-agent Reinforcement Learning. AAMAS Roxana Radulescu, Peter Vrancx, Ann Nowé
2017	J	`jnl`	Analysing Congestion Problems in Multi-agent Reinforcement Learning. CoRR Roxana Radulescu, Peter Vrancx, Ann Nowé
2017	J	`jnl`	Direct Load Control of Thermostatically Controlled Loads Based on Sparse Observations Using Deep Reinforcement Learning. CoRR Frederik Ruelens, Bert J. Claessens, Peter Vrancx, Fred Spiessens, Geert Deconinck
2017	—	`conf`	Efficient Evaluation of Influenza Mitigation Strategies Using Preventive Bandits. AAMAS Workshops (Visionary Papers) Pieter Libin, Timothy Verstraeten, Kristof Theys, Diederik M. Roijers, Peter Vrancx, Ann Nowé
2017	J	`jnl`	Forecasting day-ahead electricity prices in Europe: the importance of considering market integration. CoRR Jesus Lago, Fjo De Ridder, Peter Vrancx, Bart De Schutter
2017	J	`jnl`	Learning with Options that Terminate Off-Policy. CoRR Anna Harutyunyan, Peter Vrancx, Pierre-Luc Bacon, Doina Precup, Ann Nowé
2017	J	`jnl`	Multi-objectivization and ensembles of shapings in reinforcement learning. Neurocomputing Tim Brys, Anna Harutyunyan, Peter Vrancx, Ann Nowé, Matthew E. Taylor
2017	J	`jnl`	Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets. CoRR Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan, Peter Vrancx, Ann Nowé
2016	J	`jnl`	A reinforcement learning approach to coordinate exploration with limited communication in continuous action games. Knowl. Eng. Rev. Abdel Rodríguez, Peter Vrancx, Ricardo Grau, Ann Nowé
2016	J	`jnl`	Convolutional Neural Networks For Automatic State-Time Feature Extraction in Reinforcement Learning Applied to Residential Load Control. CoRR Bert J. Claessens, Peter Vrancx, Frederik Ruelens
2016	J	`jnl`	Predicting Seat-Off and Detecting Start-of-Assistance Events for Assisting Sit-to-Stand With an Exoskeleton. IEEE Robotics Autom. Lett. Kevin Tanghe, Anna Harutyunyan, Erwin Aertbeliën, Friedl De Groote, Joris De Schutter, Peter Vrancx, Ann Nowé
2016	J	`jnl`	Preface to the special issue: adaptive learning agents. Knowl. Eng. Rev. Peter Vrancx, Enda Howley, Matt Knudson
2015	J	`jnl`	A Reinforcement Learning Approach for Interdomain Routing with Link Prices. ACM Trans. Auton. Adapt. Syst. Peter Vrancx, Pasquale Gurzi, Abdel Rodríguez, Kris Steenhaut, Ann Nowé
2015	J	`jnl`	An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments. CoRR Denis Steckelmacher, Peter Vrancx
2015	A*	`conf`	Expressing Arbitrary Reward Functions as Potential-Based Advice. AAAI Anna Harutyunyan, Sam Devlin, Peter Vrancx, Ann Nowé
2015	A	`conf`	Multi-Scale Reward Shaping via an Off-Policy Ensemble. AAMAS Anna Harutyunyan, Tim Brys, Peter Vrancx, Ann Nowé
2015	J	`jnl`	Off-Policy Reward Shaping with Ensembles. CoRR Anna Harutyunyan, Tim Brys, Peter Vrancx, Ann Nowé
2015	A	`conf`	Shaping Mario with Human Advice. AAMAS Anna Harutyunyan, Tim Brys, Peter Vrancx, Ann Nowé
2014	B	`conf`	Multi-objective χ-Armed bandits. IJCNN Kristof Van Moffaert, Kevin Van Vaerenbergh, Peter Vrancx, Ann Nowé
2014	B	`conf`	Multi-objectivization of reinforcement learning problems by reward shaping. IJCNN Tim Brys, Anna Harutyunyan, Peter Vrancx, Matthew E. Taylor, Daniel Kudenko, Ann Nowé
2014	A	`conf`	Off-Policy Shaping Ensembles in Reinforcement Learning. ECAI Anna Harutyunyan, Tim Brys, Peter Vrancx, Ann Nowé
2014	J	`jnl`	Off-Policy Shaping Ensembles in Reinforcement Learning. CoRR Anna Harutyunyan, Tim Brys, Peter Vrancx, Ann Nowé
2013	—	`conf`	Model-free learning of wire winding control. ASCC Abdel Rodríguez, Peter Vrancx, Ann Nowé, Erik Hostens
2013	—	`conf`	Reinforcement Learning for Multi-purpose Schedules. ICAART (2) Kristof Van Moffaert, Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2012	—	`ed.`	Adaptive and Learning Agents - International Workshop, ALA 2011, Held at AAMAS 2011, Taipei, Taiwan, May 2, 2011, Revised Selected Papers ALA Peter Vrancx, Matthew Knudson, Marek Grzes
2012	A	`conf`	An RL approach to common-interest continuous action games. AAMAS Abdel Rodríguez, Peter Vrancx, Ricardo Grau Ábalo, Ann Nowé
2012	—	`ch.`	Game Theory and Multi-agent Reinforcement Learning. Reinforcement Learning Ann Nowé, Peter Vrancx, Yann-Michaël De Hauwere
2012	B	`conf`	Improving wet clutch engagement with reinforcement learning. IJCNN Kevin Van Vaerenbergh, Abdel Rodríguez, Matteo Gagliolo, Peter Vrancx, Ann Nowé, Julian Stoev, Stijn Goossens, Gregory Pinte, Wim Symens
2011	—	`conf`	Adaptive State Representations for Multi-agent Reinforcement Learning. ICAART (2) Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2011	C	`conf`	Learning a pricing strategy in multi-domain DWDM networks. LANMAN Pasquale Gurzi, Kris Steenhaut, Ann Nowé, Peter Vrancx
2011	C	`conf`	Local Coordination in Online Distributed Constraint Optimization Problems. EUMAS Tim Brys, Yann-Michaël De Hauwere, Ann Nowé, Peter Vrancx
2011	—	`conf`	Solving Sparse Delayed Coordination Problems in Multi-Agent Reinforcement Learning. ALA Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2011	A	`conf`	Solving delayed coordination problems in MAS. AAMAS Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2011	—	`conf`	Transfer Learning for Multi-agent Coordination. ICAART (2) Peter Vrancx, Yann-Michaël De Hauwere, Ann Nowé
2010	J	`jnl`	Analyzing the dynamics of stigmergetic interactions through pheromone games. Theor. Comput. Sci. Peter Vrancx, Katja Verbeeck, Ann Nowé
2010	J	`jnl`	Generalized learning automata for multi-agent reinforcement learning. AI Commun. Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2010	A	`conf`	Learning multi-agent state space representations. AAMAS Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2010	—	`ch.`	Multi-Agent Systems and Large State Spaces. Agent and Multi-agent Technology for Internet and Enterprise Systems Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2010	A	`conf`	Taking turns in general sum Markov games. AAMAS Peter Vrancx, Katja Verbeeck, Ann Nowé
2008	J	`jnl`	Decentralized Learning in Markov Games. IEEE Trans. Syst. Man Cybern. Part B Peter Vrancx, Katja Verbeeck, Ann Nowé
2008	—	`conf`	Switching dynamics of multi-agent learning. AAMAS (1) Peter Vrancx, Karl Tuyls, Ronald L. Westra
2008	—	`conf`	Using Generalized Learning Automata for State Space Aggregation in MAS. KES (1) Yann-Michaël De Hauwere, Peter Vrancx, Ann Nowé
2007	—	`conf`	Networks of Learning Automata and Limiting Games. Adaptive Agents and Multi-Agents Systems Peter Vrancx, Katja Verbeeck, Ann Nowé
2007	—	`conf`	Optimal Convergence in Multi-Agent MDPs. KES (3) Peter Vrancx, Katja Verbeeck, Ann Nowé
2006	—	`conf`	Analyzing Stigmergetic Algorithms Through Automata Games. KDECB Peter Vrancx, Katja Verbeeck, Ann Nowé
2006	—	`conf`	Using Pheromone Repulsion to Find Disjoint Paths. ANTS Workshop Peter Vrancx, Ann Nowé
2005	A	`conf`	A model based on ant colony system and rough set theory to feature selection. GECCO Rafael Bello, Ann Nowé, Yaile Caballero, Yudel Gómez, Peter Vrancx
2005	—	`conf`	Multi-type ACO for Light Path Protection. LAMAS Peter Vrancx, Ann Nowé, Kris Steenhaut
2005	C	`conf`	Multi-type ACO for light path protection. EUMAS Peter Vrancx, Ann Nowé, Kris Steenhaut
2004	—	`conf`	Multi-type Ant Colony: The Edge Disjoint Paths Problem. ANTS Workshop Ann Nowé, Katja Verbeeck, Peter Vrancx