< Terug naar vorige pagina
Onderzoeker
Anna Harutyunyan
- Trefwoorden:Informatica
Affiliaties
- Faculteit van de Wetenschappen (Faculteit)
Lid
Vanaf11 aug 2015 → 30 mrt 2018 - Informatica en Toegepaste Informatica (Departement)
Lid
Vanaf15 feb 2013 → 31 dec 2017 - Computationele Modelering Lab (Onderzoeksgroep)
Lid
Vanaf15 feb 2013 → 31 dec 2016
Publicaties
1 - 10 van 15
- Reinforcement Learning in POMDPs with Memoryless Options and Option-Observation Initiation Sets(2018)Series: AAAI Conference on Artificial Intelligence
Auteurs: Denis Steckelmacher, Diederik M. Roijers, Anna Harutyunyan, Peter Vrancx, Helene Plisnier, Ann Nowe
Pagina's: 4099-4106Aantal pagina's: 8 - Learning with options that terminate off-policy(2018)
Auteurs: Anna Harutyunyan, Pierre Luc Bacon, Doina Precup, Ann Nowe
Pagina's: 3173-3182Aantal pagina's: 10 - Multi-objectivization and ensembles of shapings in reinforcement learning(2017)
Auteurs: Tim Brys, Anna Harutyunyan, Peter Vrancx, Ann Nowe, Matthew Taylor
Pagina's: 48-59 - Human Guided Ensemble Learning in StarCraft(2016)
Auteurs: Tom Jaspers, Robrecht Conjaerts, Tim Brys, Anna Harutyunyan
Pagina's: 99-105Aantal pagina's: 7 - Safe and Efficient Off-Policy Reinforcement Learning(2016)
Auteurs: Remi Munos, Tom Stepleton, Anna Harutyunyan, Marc G. Bellemare
Pagina's: 1054-1062 - Predicting Seat-Off and Detecting Start-of-Assistance Events for Assisting Sit-to-Stand with an Exoskeleton(2016)
Auteurs: Kevin Tanghe, Anna Harutyunyan, Erwin Aertbelien, Friedl De Groote, Joris De Schutter, Ann Nowe
- Shaping Mario with Human Advice (Demonstration)(2015)
Auteurs: Anna Harutyunyan, Tim Brys, Ann Nowe
Pagina's: 1913-1914Aantal pagina's: 2 - Expressing Arbitrary Reward Functions as Potential-Based Advice(2015)Series: Twenty-Ninth AAAI Conference on Artificial Intelligence
Auteurs: Anna Harutyunyan, Sam Devlin, Ann Nowe
Aantal pagina's: 7 - Multi-Scale Reward Shaping via an Off-Policy Ensemble(2015)
Auteurs: Anna Harutyunyan, Tim Brys, Ann Nowe
Pagina's: 1641–1642Aantal pagina's: 2 - Policy Transfer using Reward Shaping(2015)
Auteurs: Tim Brys, Anna Harutyunyan, Matthew E. Taylor, Ann Nowe
Pagina's: 181-188Aantal pagina's: 8