Nitarshan Rajkumar

Publications
Influence

In Search of Robust Measures of Generalization

G. Dziugaite, Alexandre Drouin, Daniel M. Roy
Computer Science
NeurIPS
22 October 2020

This work addresses the question of how to evaluate generalization bounds empirically and argues that generalization measures should instead be evaluated within the framework of distributional robustness.

View PDF on arXiv

Pretraining Representations for Data-Efficient Reinforcement Learning

Max Schwarzer, Nitarshan Rajkumar, Aaron C. Courville
Computer Science
NeurIPS
9 June 2021

This work uses unlabeled data to pretrain an encoder which is then finetuned on a small amount of task-specific data, and employs a combination of latent dynamics modelling and unsupervised goal-conditioned RL to encourage learning representations which capture diverse aspects of the underlying MDP.

View PDF on arXiv

Evaluating the Text-to-SQL Capabilities of Large Language Models

Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau
Computer Science
ArXiv
15 March 2022

It is demonstrated on the GeoQuery and Scholar benchmarks that a small number of in-domain examples provided in the prompt enables Codex to perform better than state-of-the-art models ﬁnetuned on such few-shot examples.

View PDF on arXiv

Myriad: a real-world testbed to bridge trajectory optimization and deep learning

Nikolaus H. R. Howe, Simon Dufort-Labb'e, Nitarshan Rajkumar, Pierre-Luc Bacon
Computer Science
ArXiv
22 February 2022

The Myriad model leverages an implicit planning module over neural ordinary differential equations, enabling simultaneous learning and planning with complex environment dynamics, and the Myriad repository is used to showcase a novel approach for learning and control tasks.

View PDF on arXiv

Recommended Authors