-
Achkan Salehi
- Postdoctoral researcher
- Team: Amac
- Email: salehi@isir.upmc.fr
- Bio: My current works lie at the intersection of Reinforcement Learning and evolutionary methods, mainly in the context of the H2020 european FET project VeriDREAM (https://www.veridream.eu/). I worked on sensor fusion and SLAM for autonomous navigation during my Phd. Before joining the ISIR, I worked as a research engineer at SLAMCore Ltd, mainly on problems related to Machine Learning for SLAM and more generally spatial AI.
Publications
-
Achkan Salehi, Alexandre Coninx, Stephane Doncieux. Few-shot Quality-Diversity Optimization. IEEE Robotics and Automation Letters, In press, 7 (2), pp.1-10. ⟨10.1109/LRA.2022.3148438⟩. ⟨hal-03569179⟩
[ HTTP ]
-
Achkan Salehi, Alexandre Coninx, Stephane Doncieux. Geodesics, Non-linearities and the Archive of Novelty Search. GECCO '22: Genetic and Evolutionary Computation Conference, Jul 2022, Boston Massachusetts, United States. pp.156-159, ⟨10.1145/3520304.3528944⟩. ⟨hal-03661188⟩
[ HTTP ]
-
Salehi Achkan, Alexandre Coninx, Stephane Doncieux. BR-NS: an Archive-less Approach to Novelty Search. The Genetic and Evolutionary Computation Conference, Jul 2021, Lille, France. pp.172-179, ⟨10.1145/3449639.3459303⟩. ⟨hal-03344296⟩
[ HTTP ]
