Picture for Oleh Rybkin

Oleh Rybkin

Planning Goals for Exploration

Mar 23, 2023
Edward S. Hu, Richard Chang, Oleh Rybkin, Dinesh Jayaraman

Figure 1 for Planning Goals for Exploration

Figure 2 for Planning Goals for Exploration

Figure 3 for Planning Goals for Exploration

Figure 4 for Planning Goals for Exploration

* Camera Ready version for ICLR2023 Spotlight

Access Paper or Ask Questions

Learning General World Models in a Handful of Reward-Free Deployments

Oct 23, 2022
Yingchen Xu, Jack Parker-Holder, Aldo Pacchiano, Philip J. Ball, Oleh Rybkin, Stephen J. Roberts, Tim Rocktäschel, Edward Grefenstette

Figure 1 for Learning General World Models in a Handful of Reward-Free Deployments

Figure 2 for Learning General World Models in a Handful of Reward-Free Deployments

Figure 3 for Learning General World Models in a Handful of Reward-Free Deployments

Figure 4 for Learning General World Models in a Handful of Reward-Free Deployments

* To be published at NeurIPS 2022. Code and videos available at https://ycxuyingchen.github.io/cascade/

Access Paper or Ask Questions

Discovering and Achieving Goals via World Models

Oct 18, 2021
Russell Mendonca, Oleh Rybkin, Kostas Daniilidis, Danijar Hafner, Deepak Pathak

Figure 1 for Discovering and Achieving Goals via World Models

Figure 2 for Discovering and Achieving Goals via World Models

Figure 3 for Discovering and Achieving Goals via World Models

Figure 4 for Discovering and Achieving Goals via World Models

* NeurIPS 2021. First two authors contributed equally. Website at https://orybkin.github.io/lexa/

Access Paper or Ask Questions

Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

Jul 28, 2021
Edward S. Hu, Kun Huang, Oleh Rybkin, Dinesh Jayaraman

Figure 1 for Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

Figure 2 for Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

Figure 3 for Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

Figure 4 for Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

* Website: https://hueds.github.io/rac/ Updated typos

Access Paper or Ask Questions

Model-Based Reinforcement Learning via Latent-Space Collocation

Jun 24, 2021
Oleh Rybkin, Chuning Zhu, Anusha Nagabandi, Kostas Daniilidis, Igor Mordatch, Sergey Levine

Figure 1 for Model-Based Reinforcement Learning via Latent-Space Collocation

Figure 2 for Model-Based Reinforcement Learning via Latent-Space Collocation

Figure 3 for Model-Based Reinforcement Learning via Latent-Space Collocation

Figure 4 for Model-Based Reinforcement Learning via Latent-Space Collocation

* International Conference on Machine Learning (ICML), 2021. Videos and code at https://orybkin.github.io/latco/

Access Paper or Ask Questions

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Jun 23, 2020
Karl Pertsch, Oleh Rybkin, Frederik Ebert, Chelsea Finn, Dinesh Jayaraman, Sergey Levine

Figure 1 for Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Figure 2 for Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Figure 3 for Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

Figure 4 for Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

* Project page: orybkin.github.io/video-gcp

Access Paper or Ask Questions

Simple and Effective VAE Training with Calibrated Decoders

Jun 23, 2020
Oleh Rybkin, Kostas Daniilidis, Sergey Levine

Figure 1 for Simple and Effective VAE Training with Calibrated Decoders

Figure 2 for Simple and Effective VAE Training with Calibrated Decoders

Figure 3 for Simple and Effective VAE Training with Calibrated Decoders

Figure 4 for Simple and Effective VAE Training with Calibrated Decoders

* Project website: \url{https://orybkin.github.io/sigma-vae/}

Access Paper or Ask Questions