Research Scientist DeepMind, London
Keywords: reinforcement learning, temporal abstraction, off-policy learning
News
The news have not been updated since 2019
- [December 2019] Excited to present our paper on Hindsight Credit Assignment as a spotlight at NeurIPS in Vancouver
- [August 2019] Had an amazing time preparing and teaching the deep reinforcement lecture at the DLRL summer school in Edmonton (video)
- [July 2019] Back to updating the website! Excited to travel to Montreal for RLDM in a few days to present the Termination Critic, and speak about inductive biases
- [January 2018] I completed my PhD and have joined DeepMind in London. My thesis can be found here.
- [December 2017] Our paper Learning with Options that Terminate Off-Policy won the best paper award at the Hierarchical Reinforcement Learning workshop at NIPS!
About
Anna was born and raised in Yerevan, Armenia. Her winding academic path has led her through post-Soviet mathematical landscapes and Oregonian planar graphs, to eventually and almost accidentally, reinforcement learning in 2013. She received her PhD in 2018 from the Free University of Brussels, with a thesis titled “Beyond single step temporal difference learning”. Since then she has been a research scientist at DeepMind, continuing to ask questions beyond the convention. A student of wisdom traditions, she is now interested in philosophically and metaphysically motivated technology, poetics of agents, and seeks to align the computational metaphors underlying our algorithms with deeper truths about human and more-than-human intelligence.
Her (likely outdated) CV can be found here