S
Sujay Bajracharya
Researcher at Cleveland State University
Publications - 5
Citations - 93
Sujay Bajracharya is an academic researcher from Cleveland State University. The author has contributed to research in topics: Human–robot interaction & Dialog box. The author has an hindex of 3, co-authored 5 publications receiving 21 citations.
Papers
More filters
Posted Content
PLAS: Latent Action Space for Offline Reinforcement Learning
TL;DR: This work proposes to simply learn the Policy in the Latent Action Space (PLAS) such that this requirement is naturally satisfied, and demonstrates that this method provides competitive performance consistently across various continuous control tasks and different types of datasets, outperforming existing offline reinforcement learning methods with explicit constraints.
Posted Content
Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialog
TL;DR: This article developed a dialog agent for robots that is able to interpret user commands using a semantic parser, while asking clarification questions using a probabilistic dialog manager, which can augment its knowledge base and improve its language capabilities by learning from dialog experiences.
Proceedings ArticleDOI
Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialog
TL;DR: A dialog agent for robots that is able to interpret user commands using a semantic parser, while asking clarification questions using a probabilistic dialog manager to augment its knowledge base and improve its language capabilities by learning from dialog experiences.
PLAS: Latent Action Space for Offline Reinforcement Learning
TL;DR: In this article, the policy in the Latent Action Space (PLAS) is learned to select actions within the support of the dataset during training, such that this requirement is naturally satisfied.
Posted Content
FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy.
TL;DR: In this paper, optical flow is used as both an input and an action representation to improve performance of goal-directed cloth manipulation, a challenging task due to the deformability of cloth.