Sotabase

Career

· Postdoctoral Researcher, Stanford University2020–2023
· Postdoctoral Researcher, Aalto University2018–2019
· Postdoctoral Researcher, KTH Royal Institute of Technology2018–2020
· PhD Student, KTH Royal Institute of Technology2013–2018
· M.S. in Systems, Control and Robotics, KTH Royal Institute of Technology2010–2013
· B.S. in Electrical Engineering, Ferdowsi University of Mashhad2006–2010
· Machine learning research engineer, Embark Studios
· Reinforcement Learning Research Engineer, Embark Studios

Publications (33)

Deep predictive policy training using reinforcement learning
IEEE/RJS International Conference on Intelligent RObots and Systems · 2017
133
cited
Meta Reinforcement Learning for Sim-to-real Domain Adaptation
IEEE International Conference on Robotics and Automation · 2019
115
cited
Human-Centered Collaborative Robots With Deep Reinforcement Learning
IEEE Robotics and Automation Letters · 2020
76
cited
Meta-Learning for Multi-objective Reinforcement Learning
IEEE/RJS International Conference on Intelligent RObots and Systems · 2018
64
cited
A sensorimotor reinforcement learning framework for physical Human-Robot Interaction
IEEE/RJS International Conference on Intelligent RObots and Systems · 2016
52
cited
Affordance Learning for End-to-End Visuomotor Robot Control
IEEE/RJS International Conference on Intelligent RObots and Systems · 2019
50
cited
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
IEEE/RJS International Conference on Intelligent RObots and Systems · 2021
45
cited
Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments
IEEE/RJS International Conference on Intelligent RObots and Systems · 2018
45
cited
LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning
Neural Information Processing Systems · 2022
44
cited
Imitating by Generating: Deep Generative Models for Imitation of Interactive Tasks
Frontiers in Robotics and AI · 2019
31
cited
Back to the Manifold: Recovering from Out-of-Distribution States
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
22
cited
Latent-Variable Advantage-Weighted Policy Optimization for Offline RL
arXiv.org · 2022
17
cited
Adversarial Feature Training for Generalizable Robotic Visuomotor Control
IEEE International Conference on Robotics and Automation · 2019
13
cited
A sensorimotor approach for self-learning of hand-eye coordination
IEEE/RJS International Conference on Intelligent RObots and Systems · 2015
10
cited
Data-efficient visuomotor policy training using reinforcement learning and generative models
arXiv.org · 2020
9
cited
Few-Shot Model-Based Adaptation in Noisy Conditions
IEEE Robotics and Automation Letters · 2020
9
cited
Self-learning and adaptation in a sensorimotor framework
IEEE International Conference on Robotics and Automation · 2016
9
cited
Co-adaptive Human-Robot Cooperation: Summary and Challenges
Unmanned Systems · 2021
8
cited
Coordinating With a Robot Partner Affects Neural Processing Related to Action Monitoring
bioRxiv · 2021
8
cited
Learning visual forward models to compensate for self-induced image motion
IEEE International Symposium on Robot and Human Interactive Communication · 2014
6
cited
Sotabase
Ali Ghadirzadeh | Researcher Profile | Sotabase | Sotabase