94 citations · 399 across the 21 of their papers we have counts for
22 papers
Genie: Generative Interactive Environments
Jake Bruce, Michael Dennis, Ashley Edwards +22
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless…
AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
Michaël Mathieu, Sherjil Ozair, Srivatsan Srinivasan +21
StarCraft II is one of the most challenging simulated reinforcement learning environments; it is partially observable, stochastic, multi-agent, and mastering StarCraft II requires…
RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
Konstantinos Bousmalis, Giulia Vezzani, Dushyant Rao +36
The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learnin…
A Generalist Agent
Scott Reed, Konrad Zolna, Emilio Parisotto +17
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we…
Robust Learning-Augmented Caching: An Experimental Study
Jakub Chłędowski, Adam Polak, Bartosz Szabucki +1
Effective caching is crucial for the performance of modern-day computing systems. A key optimization problem arising in caching -- which item to evict to make room for a new item -…
Regularized Behavior Value Estimation
Caglar Gulcehre, Sergio Gómez Colmenarejo, Ziyu Wang +7
Offline reinforcement learning restricts the learning process to rely only on logged-data without access to an environment. While this enables real-world applications, it also pose…
Semi-supervised reward learning for offline reinforcement learning
Ksenia Konyushkova, Konrad Zolna, Yusuf Aytar +4
In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such a…
Offline Learning from Demonstrations and Unlabeled Experience
Konrad Zolna, Alexander Novikov, Ksenia Konyushkova +6
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. Howev…
Hyperparameter Selection for Offline Reinforcement Learning
Tom Le Paine, Cosmin Paduraru, Andrea Michi +5
Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection m…
Critic Regularized Regression
Ziyu Wang, Alexander Novikov, Konrad Zolna +8
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It…
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
Caglar Gulcehre, Ziyu Wang, Alexander Novikov +15
Offline methods for reinforcement learning have a potential to help bridge the gap between reinforcement learning research and real-world applications. They make it possible to lea…
Combating False Negatives in Adversarial Imitation Learning
Konrad Zolna, Chitwan Saharia, Leonard Boussioux +4
In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained…
Task-Relevant Adversarial Imitation Learning
Konrad Zolna, Scott Reed, Alexander Novikov +6
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. W…
Scaling data-driven robotics with reward sketching and batch reinforcement learning
Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov +13
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions. We show h…
The Dynamics of Handwriting Improves the Automated Diagnosis of Dysgraphia
Konrad Zolna, Thibault Asselborn, Caroline Jolly +4
Handwriting disorder (termed dysgraphia) is a far from a singular problem as nearly 8.6% of the population in France is considered dysgraphic. Moreover, research highlights the fun…
Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
Michał Zając, Konrad Zolna, Stanisław Jastrzębski
Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch bet…
Reinforced Imitation in Heterogeneous Action Space
Konrad Zolna, Negar Rostamzadeh, Yoshua Bengio +2
Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an…
Adversarial Framing for Image and Video Classification
Konrad Zolna, Michal Zajac, Negar Rostamzadeh +1
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it…
Focused Hierarchical RNNs for Conditional Sequence Processing
Nan Rosemary Ke, Konrad Zolna, Alessandro Sordoni +6
Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of enco…
Classifier-agnostic saliency map extraction
Konrad Zolna, Krzysztof J. Geras, Kyunghyun Cho
Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependenc…
Fraternal Dropout
Konrad Zolna, Devansh Arpit, Dendi Suhubdy +1
Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is know…
Improving the Performance of Neural Networks in Regression Tasks Using Drawering
Konrad Zolna
The method presented extends a given regression neural network to make its performance improve. The modification affects the learning procedure only, hence the extension may be eas…