← Authors

Denis Yarats

15 papers · 2017–2022 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (32) πŸ‘‘ Triple Crown πŸ† Grand Slam 🧬 Topic Evolution ❓ The Questioner πŸ’Ž Century Club (15) πŸ—ƒοΈ Keyword Collector (69) ⚑ Prolific Year (6) πŸ”₯ Unstoppable (6)

Conferences

ICML (4) ICLR (3) NIPS (3) AAAI (2) CORL (1) EMNLP (1) L4DC (1)

Top co-authors

Rob Fergus (5) Ilya Kostrikov (3) Mike Lewis (3) Brandon Amos (3) Lerrel Pinto (3) Jerry Ma (2) Alessandro Lazaric (2) Hengyuan Hu (1) David Grangier (1) Aravind Rajeswaran (1)

Research topics

Methods (1)

Keywords

continuous control (3) reinforcement learning (3) dialogue system (2) representation learning (2) latent representation (2) domain generalization (1) machine translation (1) policy optimization (1) attention mechanism (1) self-supervised learning (1) imitation learning (1) data augmentation (1) dialogue generation (1) policy learning (1) behavior cloning (1) optimal transport (1) inverse reinforcement learning (1) mutual information (1) neural network optimization (1) structured prediction (1)

Papers

Watch and Match: Supercharging Imitation with Regularized Optimal Transport CORL 2022
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning ICLR 2022
Unsupervised Reinforcement Learning with Contrastive Intrinsic Control NIPS 2022
On the Model-Based Stochastic Value Gradient for Continuous Reinforcement Learning L4DC 2021
Automatic Data Augmentation for Generalization in Reinforcement Learning NIPS 2021
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels ICLR 2021
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images AAAI 2021
On the Adequacy of Untuned Warmup for Adaptive Optimization AAAI 2021
Reinforcement Learning with Prototypical Representations ICML 2021
The Differentiable Cross-Entropy Method ICML 2020
Quasi-hyperbolic momentum and Adam for deep learning ICLR 2019
Hierarchical Decision Making by Generating and Following Natural Language Instructions NIPS 2019
Hierarchical Text Generation and Planning for Strategic Dialogue ICML 2018
Convolutional Sequence to Sequence Learning ICML 2017
Deal or No Deal? End-to-End Learning of Negotiation Dialogues EMNLP 2017