Sotabase

Career

· Intern, Google Brain2019–
· Visiting Student Researcher, Tokyo Institute of Technology2017–2017
· PhD in Computer Science, University of Pennsylvania2017–2023
· Visiting Student Researcher, INRIA2016–2016
· Bachelor's Degree with Honours in Computer Science, Czech Technical University in Prague2014–2017
· Reinforcement Learning Researcher, Cursor
· Intern, DeepMind
· Postdoctoral Researcher, UC Berkeley BAIR lab
· Research Scientist, xAI

Publications (32)

Planning to Explore via Self-Supervised World Models
International Conference on Machine Learning · 2020
473
cited
Discovering and Achieving Goals via World Models
Neural Information Processing Systems · 2021
160
cited
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Conference on Robot Learning · 2020
113
cited
Simple and Effective VAE Training with Calibrated Decoders
International Conference on Machine Learning · 2020
112
cited
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Neural Information Processing Systems · 2020
81
cited
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
International Conference on Learning Representations · 2023
72
cited
Learning Predictive Models From Observation and Interaction
European Conference on Computer Vision · 2019
63
cited
Model-Based Reinforcement Learning via Latent-Space Collocation
International Conference on Machine Learning · 2021
44
cited
Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning
Conference on Learning for Dynamics & Control · 2019
31
cited
Planning Goals for Exploration
International Conference on Learning Representations · 2023
31
cited
Learning what you can do before doing anything
International Conference on Learning Representations · 2018
30
cited
Privileged Sensing Scaffolds Reinforcement Learning
International Conference on Learning Representations · 2024
19
cited
Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos
arXiv.org · 2025
14
cited
Learning General World Models in a Handful of Reward-Free Deployments
Neural Information Processing Systems · 2022
11
cited
Value-Based Deep RL Scales Predictably
International Conference on Machine Learning · 2025
9
cited
Latent Diffusion Planning for Imitation Learning
International Conference on Machine Learning · 2025
8
cited
KeyIn: Discovering Subgoal Structure with Keyframe-based Video Prediction
arXiv.org · 2019
7
cited
Unsupervised Learning of Sensorimotor Affordances by Stochastic Future Prediction
arXiv.org · 2018
6
cited
Perception-Driven Curiosity with Bayesian Surprise
2019
5
cited
Compute-Optimal Scaling for Value-Based Deep RL
arXiv.org · 2025
2
cited
Sotabase
Oleh Rybkin | Researcher Profile | Sotabase | Sotabase