Tuomas Haarnoja

I am a PhD candidate in the Berkeley AI Research Lab (BAIR), advised by Pieter Abbeel and Sergey Levine. I am interested in building better understanding of deep reinforcement learning algorithms and developing new solution to problems inspired by real-world robotic applications, requiring good sample complexity and safe exploration. I am mostly known for my work on maximum entropy reinforcement learning, which provides a theoretically grounded framework for learning stochastic policies that are both sample efficient and reliable, and its applications to robotic manipulation and locomotion.

I received a master's degree in Space Robotics and Automation from Luleå University of Technology, Sweden, and Aalto University, Finland, and worked as a research scientist at VTT Technical Research Centre of Finland before I joined BAIR.

Email  |  Twitter |  Linkedin  |  Google Scholar  |  GitHub

Publications
Below is a representative list of my current research. For a complete list, see my Google Scholar page.

Latent Space Policies for Hierarchical Reinforcement Learning
Tuomas Haarnoja, Kristian Hartikainen, Pieter Abbeel, and Sergey Levine
International Conference on Machine Learning (ICML), 2018.
paper  |  videos  |  code

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine
International Conference on Machine Learning (ICML), 2018.
paper  |  videos  |  code

Composable Deep Reinforcement Learning for Robotic Manipulation
Tuomas Haarnoja, Vitchyr Pong, Aurick Zhou, Murtaza Dalal, Pieter Abbeel, Sergey Levine
International Conference on Robotics and Automation (ICRA), 2018.
paper  |  videos  |  code

Reinforcement Learning with Deep Energy-Based Policies
Tuomas Haarnoja*, Haoran Tang*, Pieter Abbeel, Sergey Levine
International Conference on Machine Learning (ICML), 2017.
paper  |  videos  |  code

Backprop KF: Learning Discriminative Deterministic State Estimators
Tuomas Haarnoja, Anurag Ajay, Sergey Levine, Pieter Abbeel
Neural Information Processing Systems (NIPS), 2016.
paper

Model-Based Velocity Control for Limit-Cycle Walking
Tuomas Haarnoja, José-Luis Peralta, and Aarne Halme
International Conference on Intelligent Robots and Systems (IROS), 2011.
paper

Assessment of Limit-Cycle-Based Control on 2D Kneed Biped
José-Luis Peralta, Tuomas Haarnoja, Tomi Ylikorpi, and Aarne Halme
International Conference on Robotics and Automation (ICRA), 2011.
paper

Idle State Stability, Limit Cycle Walking & Regenerative Walking: Towards Long Time Autonomy in Bipeds
José-Luis Peralta, Tuomas Haarnoja, Tomi Ylikorpi, and Aarne Halme
International Conference on Climbing and Walking Robots (CLAWAR), 2010.
paper

Teaching

Deep Reinforcement Learning Bootcamp
26-27 August 2017, UC Berkeley, Teaching Assistant

CS188/289A - Introduction to Machine Learning
Spring 2016, UC Berkeley, Graduate Student Instructor

AS-0.1101 - Basic course on C programming,
Spring 2007, Helsinki University of Technology, Teaching Assistant


Looking for a nice template? Check this one out!