Nitarshan Rajkumar

4 papers · 2020–2023 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

NeurIPS (3) ICLR (1)

Top co-authors

Ioannis Mitliagkas (1) Linbo Wang (1) David Krueger (1) Pierre-Luc Bacon (1) Philip Bachman (1) Sara Hooker (1) Brady Neal (1) Tegan Maharaj (1) Nikolaus Howe (1) Simon Dufort-Labbé (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Learning Types (3) Core AI (2) Deep Learning (1) Reinforcement Learning (1) Applications (1) Core Methods (1) Learning Paradigms (1) Methods (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

representation learning (1) reinforcement learning (1) imitation learning (1) deep learning (1) optimal control (1) trajectory optimization (1) generalization error (1) excess risk (1) distributional robustness (1) generalization bound (1) neural ordinary differential equation (1) training dynamics (1) data quality (1) dynamics learning (1) data-efficient reinforcement learning (1) neural network (1) metadata inference (1) unsupervised goal-conditioned rl (1) latent dynamics modelling (1) mislabeled example (1)

Papers

Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics ICLR 2023 Myriad: a real-world testbed to bridge trajectory optimization and deep learning NeurIPS 2022 Pretraining Representations for Data-Efficient Reinforcement Learning NeurIPS 2021 In search of robust measures of generalization NeurIPS 2020