|
Hi! I am Oleh, a Ph.D. student in the GRASP laboratory at the University of Pennsylvania advised by Kostas Daniilidis. I work on visual model-based reinforcement learning. I am building agents that gain understanding of their environment by learning internal world models. Recently, I've been working on self-supervised reinforcement learning agents, long-horizon planning, and building better predictive models.I received my bachelor's degree from Czech Technical University in Prague, where I worked with Tomas Pajdla. I've spent time at INRIA with Josef Sivic, TiTech with Akihiko Torii, and UC Berkeley with Sergey Levine, Dinesh Jayaraman, and Chelsea Finn.
Google Scholar / GitHub / CV / Email / Twitter |
|
|
 
|
Commonly used uncalibrated decoders adversely affect training of VAEs and sequence VAEs. However, learning appropriate calibrated decoders produces better samples, is simple to implement, and does not require the common heuristic weight on the KL divergence term. Hover/tap here to see the video. |
 
|
We use offline observations of humans jointly with online robot interaction data in a joint reinforcement learning algortihm. The resulting approach is able to learn from real-world human videos to solve challenging robotic tasks. Hover/tap here to see the video. |
 
|
We propose a hierarchical goal-conditioned predictive model that is able to scale to very long horizon visual prediction (more than 500 frames). Leveraging the model, we also propose a hierarchical visual planning algorithm that is effective at long-horizon control. Hover/tap here to see the video. |
 
|
We are able to learn action representations that generalize between robot data and passive observations of other agents (e.g. humans). This enables the use of additional diverse sources of data to train models for visual robotic control. Hover/tap here to see the video. |
 
|
We propose a visual model-based agent for self-supervised reinforcement learning. Our agent is able to adapt in a zero/few-shot setup, achieving comparable performance to supervised state-of-the-art RL. Hover/tap here to see the video. |
 
|
We discover keyframes in videos by learning to select frames that enable prediction of the entire sequence. By using the keyframe structure of the data for prediction, our method is further able to perform planning for longer horizons. Hover/tap here to see the video. |
|
We learn to discover an agent's action space along with a dynamics model from pure video data. The model can be used for model predictive control, requiring orders of magnitude fewer action-annotated videos than other methods.
|
|
|
|
 
|
MSE loss and its variants are commonly used for training and evaluation of future prediction. But is this the right thing to do? Hover/tap here to see the video. |
|
This is a list some books and shorter papers that changed my understanding of the field of AI and science in general. I hope you might find this useful too! The list is evolving, and suggestions for new reading material are welcome.
Books:
|
|
I am actively looking for students who are strongly motivated to work on a research project, including students who want to do a Master's thesis. Check out some of my work above and if you find it interesting, do send me an email!
|
|
Inspired by this template. Hosted on Eniac. |