Výsledky vyhledávání - "BHARDWAJ, ARJUN"

Report

Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning

Autor: Bhardwaj, Arjun, Rothfuss, Jonas, Sukhija, Bhavya, As, Yarden, Hutter, Marco, Coros, Stelian, Krause, Andreas

We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics. PACOH-RL meta-learns priors for the dynamics model, allowing swift adaptation to new dynam

Externí odkaz: http://arxiv.org/abs/2311.07558

Zobrazit plný text záznamu

Report

User Intent Classification using Memory Networks: A Comparative Analysis for a Limited Data Scenario

Autor: Bhardwaj, Arjun, Rudnicky, Alexander

In this report, we provide a comparative analysis of different techniques for user intent classification towards the task of app recommendation. We analyse the performance of different models and architectures for multi-label classification over a da

Externí odkaz: http://arxiv.org/abs/1706.06160

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

Extending SROIQ with Constraint Networks and Grounded Circumscription

Autor: Bhardwaj, Arjun

Developments in semantic web technologies have promoted ontological encoding of knowledge from diverse domains. However, modelling many practical domains requires more expressiveness than what the standard description logics (most prominently SROIQ)

Externí odkaz: http://arxiv.org/abs/1508.00116

Zobrazit plný text záznamu

Report

An Intuitive Procedure for Converting PDA to CFG, by Construction of Single State PDA

Autor: Bhardwaj, Arjun, Narayanaswamy, N. S.

We present here the proof for an alternative procedure to convert a Push Down Automata (PDA) into a Context Free Grammar (CFG). The procedure involves intermediate conversion to a single state PDA. In view of the authors, this conversion is conceptua

Externí odkaz: http://arxiv.org/abs/1411.0813

Zobrazit plný text záznamu

Report

GC-SROIQ(C) : Expressive Constraint Modelling and Grounded Circumscription for SROIQ

Autor: Bhardwaj, Arjun, Sangeetha

Developments in semantic web technologies have promoted ontological encoding of knowledge from diverse domains. However, modelling many practical domains requires more expressive representations schemes than what the standard description logics(DLs)

Externí odkaz: http://arxiv.org/abs/1411.0406

Zobrazit plný text záznamu