Scholar
Fabio Pardo
Google Scholar ID: LDpuKxkAAAAJ
Google DeepMind
Citations & Impact
Citations
10,712
H-index
12
i10-index
12
Publications
13
Co-authors
0
Contact
Publications
Resume
Academic Achievements
- OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion
- Ivy: Templated Deep Learning for Inter-Framework Portability
- Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking
- CoMic: Complementary Task Learning & Mimicry for Reusable Skills
- Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
- Time Limits in Reinforcement Learning
- Action Branching Architectures for Deep Reinforcement Learning
Research Experience
- 2021: Internship at DeepMind (Reinforcement Learning team), project on learning to plan.
- 2019: Internship at DeepMind (Deep Learning team), project on motor primitives and competitive self-play.
- 2015: Internship at National Institute of Informatics, Tokyo, Japan, project on deep reinforcement learning for autonomous robot navigation from vision.
- 2014: Internship at Flowers laboratory, Inria and ENSTA ParisTech, Paris, France, project on multimodal concepts emergence for a humanoid robot in interaction with a human tutor.
- 2013: Internship at Inria and AgroParisTech, Paris, France, projects on optimal decision making based on a mixture of prediction experts and homeostatic engine for reinforcement learning agents.
- 2013: Internship at Lip6, Paris, France, project on ontology visualization methods and their impact on short-term memory storage in humans.
Background
- PhD student in Machine Learning at Imperial College London, focusing on Deep Reinforcement Learning.