Sotabase

Career

· Research Scientist, DeepMind2019–
· PhD Student, Berkeley Artificial Intelligence Research Lab (BAIR)2013–2018
· PhD in Computer Science, University of California, Berkeley2013–2018
· PhD Student, University of California, Berkeley2012–2018
· Research Intern, Google AI
· MS, Space Science and Technology, Luleå University of Technology and Aalto University
· Co-founder, Stealth Robotics Startup
· BS, Automation and Systems Technology, Teknillinen korkeakoulu-Tekniska högskolan
· Research Scientist, VTT Technical Research Centre of Finland

Publications (32)

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
International Conference on Machine Learning · 2018
10,308
cited
Soft Actor-Critic Algorithms and Applications
arXiv.org · 2018
2,917
cited
Reinforcement Learning with Deep Energy-Based Policies
International Conference on Machine Learning · 2017
1,507
cited
Learning to Walk via Deep Reinforcement Learning
Robotics: Science and Systems · 2018
480
cited
Composable Deep Reinforcement Learning for Robotic Manipulation
IEEE International Conference on Robotics and Automation · 2018
244
cited
Learning agile soccer skills for a bipedal robot with deep reinforcement learning
Science Robotics · 2023
230
cited
Backprop KF: Learning Discriminative Deterministic State Estimators
Neural Information Processing Systems · 2016
214
cited
Latent Space Policies for Hierarchical Reinforcement Learning
International Conference on Machine Learning · 2018
202
cited
From Motor Control to Team Play in Simulated Humanoid Football
Sci. Robotics · 2021
153
cited
Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery
International Conference on Learning Representations · 2019
93
cited
NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields
IEEE International Conference on Robotics and Automation · 2022
71
cited
Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
arXiv.org · 2022
60
cited
Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
Conference on Robot Learning · 2024
25
cited
Acquiring Diverse Robot Skills via Maximum Entropy Deep Reinforcement Learning
2018
22
cited
Towards Real Robot Learning in the Wild: A Case Study in Bipedal Locomotion
Conference on Robot Learning · 2021
22
cited
Dynamical Distance Learning for Unsupervised and Semi-Supervised Skill Discovery
arXiv.org · 2019
14
cited
Magnetic bearing as Switched Reluctance Motor - feasibility study for bearingless Switched Reluctance Motor
International Electric Machines and Drives Conference · 2013
10
cited
Replay across Experiments: A Natural Extension of Off-Policy RL
International Conference on Learning Representations · 2023
10
cited
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
Trans. Mach. Learn. Res. · 2022
9
cited
Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data
CoLLAs · 2022
7
cited
Sotabase
Tuomas Haarnoja | Researcher Profile | Sotabase | Sotabase