61 citations · 172 across the 17 of their papers we have counts for
16 papers · 1 filter
Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching
Preston Fu, Kevin Frans, Oleh Rybkin +2
Current paradigms for training language models via reinforcement learning rely heavily on sparse outcome rewards. However, as we pursue tasks that require longer and more complicat…
Compute-Optimal Scaling for Value-Based Deep RL
Preston Fu, Oleh Rybkin, Zhiyuan Zhou +4
As models grow larger and training them becomes expensive, it becomes increasingly important to scale training recipes not just to larger models and more data, but to do so in a co…
Value-Based Deep RL Scales Predictably
Oleh Rybkin, Michal Nauman, Preston Fu +4
Scaling data and compute is critical to the success of modern ML. However, scaling demands predictability: we want methods to not only perform well with more compute or data, but a…
Privileged Sensing Scaffolds Reinforcement Learning
Edward S. Hu, James Springer, Oleh Rybkin +1
We need to look at our shoelaces as we first learn to tie them but having mastered this skill, can do it from touch alone. We call this phenomenon "sensory scaffolding": observatio…
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
Seohong Park, Oleh Rybkin, Sergey Levine
Unsupervised pre-training strategies have proven to be highly effective in natural language processing and computer vision. Likewise, unsupervised reinforcement learning (RL) holds…
Planning Goals for Exploration
Edward S. Hu, Richard Chang, Oleh Rybkin +1
Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within t…
Learning General World Models in a Handful of Reward-Free Deployments
Yingchen Xu, Jack Parker-Holder, Aldo Pacchiano +5
Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate…
Discovering and Achieving Goals via World Models
Russell Mendonca, Oleh Rybkin, Kostas Daniilidis +2
How can artificial agents learn to solve many diverse tasks in complex visual environments in the absence of any supervision? We decompose this question into two problems: discover…
Model-Based Reinforcement Learning via Latent-Space Collocation
Oleh Rybkin, Chuning Zhu, Anusha Nagabandi +3
The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-base…
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Karl Schmeckpeper, Oleh Rybkin, Kostas Daniilidis +2
Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is d…
Planning to Explore via Self-Supervised World Models
Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis +3
Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-…
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Karl Pertsch, Oleh Rybkin, Frederik Ebert +3
The ability to predict and plan into the future is fundamental for agents acting in the world. To reach a faraway goal, we predict trajectories at multiple timescales, first devisi…
Simple and Effective VAE Training with Calibrated Decoders
Oleh Rybkin, Kostas Daniilidis, Sergey Levine
Variational autoencoders (VAEs) provide an effective and simple method for modeling complex distributions. However, training VAEs often requires considerable hyperparameter tuning…
Learning Predictive Models From Observation and Interaction
Karl Schmeckpeper, Annie Xie, Oleh Rybkin +4
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated…
Keyframing the Future: Keyframe Discovery for Visual Prediction and Planning
Karl Pertsch, Oleh Rybkin, Jingyun Yang +5
Temporal observations such as videos contain essential information about the dynamics of the underlying scene, but they are often interleaved with inessential, predictable details.…
Learning what you can do before doing anything
Oleh Rybkin, Karl Pertsch, Konstantinos G. Derpanis +2
Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of t…