Anna Harutyunyan
Anna Harutyunyan
Email verificata su - Home page
Citata da
Citata da
Safe and efficient off-policy reinforcement learning
R Munos, T Stepleton, A Harutyunyan, M Bellemare
Advances in Neural Information Processing Systems, 1054-1062, 2016
Reinforcement learning from demonstration through shaping
T Brys, A Harutyunyan, HB Suay, S Chernova, ME Taylor, A Now
Twenty-fourth international joint conference on artificial intelligence, 2015
Multi-objectivization of reinforcement learning problems by reward shaping
T Brys, A Harutyunyan, P Vrancx, ME Taylor, D Kudenko, A Now
2014 international joint conference on neural networks (IJCNN), 2315-2322, 2014
Q() with Off-Policy Corrections
A Harutyunyan, MG Bellemare, T Stepleton, R Munos
International Conference on Algorithmic Learning Theory, 305-320, 2016
Expressing Arbitrary Reward Functions as Potential-Based Advice
A Harutyunyan, S Devlin, P Vrancx, A Now
Twenty-Ninth Conference on Artificial Intelligence (AAAI), 2015
Policy Transfer using Reward Shaping
T Brys, A Harutyunyan, ME Taylor, A Now
Fourteenth International Conference on Autonomous Agents and Multi-Agent…, 2015
Multi-objectivization and ensembles of shapings in reinforcement learning
T Brys, A Harutyunyan, P Vrancx, A Now, ME Taylor
Neurocomputing 263, 48-59, 2017
Predicting seat-off and detecting start-of-assistance events for assisting sit-to-stand with an exoskeleton
K Tanghe, A Harutyunyan, E Aertbelin, F De Groote, J De Schutter, ...
IEEE Robotics and Automation Letters 1 (2), 792-799, 2016
The termination critic
A Harutyunyan, W Dabney, D Borsa, N Heess, R Munos, D Precup
arXiv preprint arXiv:1902.09996, 2019
Learning with options that terminate off-policy
A Harutyunyan, P Vrancx, PL Bacon, D Precup, A Nowe
arXiv preprint arXiv:1711.03817, 2017
Real-time gait event detection based on kinematic data coupled to a biomechanical model
S Lambrecht, A Harutyunyan, K Tanghe, M Afschrift, J De Schutter, ...
Sensors 17 (4), 671, 2017
Shaping Mario with Human Advice
A Harutyunyan, T Brys, P Vrancx, A Now
Fourteenth International Conference on Autonomous Agents and Multi-Agent…, 2015
Reinforcement learning in POMDPs with memoryless options and option-observation initiation sets
D Steckelmacher, DM Roijers, A Harutyunyan, P Vrancx, H Plisnier, ...
arXiv preprint arXiv:1708.06551, 2017
Planted-model evaluation of algorithms for identifying differences between spreadsheets
A Harutyunyan, G Borradaile, C Chambers, C Scaffidi
2012 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC…, 2012
Off-Policy Shaping Ensembles in Reinforcement Learning
A Harutyunyan, T Brys, P Vrancx, A Nowe
Frontiers in Artificial Intelligence and Applications 263 (ECAI 2014), 1021…, 2014
Hindsight credit assignment
A Harutyunyan, W Dabney, T Mesnard, M Gheshlaghi Azar, B Piot, ...
Advances in neural information processing systems 32, 12488-12497, 2019
Multi-Scale Reward Shaping via an Off-Policy Ensemble
A Harutyunyan, T Brys, P Vrancx, A Now
Fourteenth International Conference on Autonomous Agents and Multi-Agent…, 2015
Maximum st-flow in directed planar graphs via shortest paths
G Borradaile, A Harutyunyan
International Workshop on Combinatorial Algorithms, 423-427, 2013
Conditional importance sampling for off-policy learning
M Rowland, A Harutyunyan, H Hasselt, D Borsa, T Schaul, R Munos, ...
International Conference on Artificial Intelligence and Statistics, 45-55, 2020
Per-decision option discounting
A Harutyunyan, P Vrancx, P Hamel, A Nowe, D Precup
International Conference on Machine Learning, 2644-2652, 2019
Il sistema al momento non pu eseguire l'operazione. Riprova pi tardi.
Articoli 1–20