Rajan Chari — accepted AI-conference papers

2024

PcLast: Discovering Plannable Continuous Latent States

Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu +8

ICML 2024poster

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision making, they ignore state reachability, hampering their perf…

Cited by 2 Source ↗PDF ↗Scholar ↗

2020

Efficient Contextual Bandits with Continuous Actions

Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins

NeurIPS 2020poster

We create a computationally tractable learning algorithm for contextual bandits with continuous actions having unknown structure. The new reduction-style algorithm composes with most supervised learning representations. We prove that this algorithm works in a general sense and verify the new funct…

Cited by 43 Source ↗PDF ↗Scholar ↗