Search Results - "Sezener, Eren"

Optimizing the depth and the direction of prospective planning using information values by Sezener, Can Eren, Dezfouli, Amir, Keramati, Mehdi

“…Evaluating the future consequences of actions is achievable by simulating a mental search tree into the future. Expanding deep trees, however, is…”
Get full text

Static and Dynamic Values of Computation in MCTS by Sezener, Eren, Dayan, Peter

“…PMLR 124:31-40, 2020 Monte-Carlo Tree Search (MCTS) is one of the most-widely used methods for planning, and has powered many recent advances in artificial…”
Get full text

A Combinatorial Perspective on Transfer Learning by Wang, Jianan, Sezener, Eren, Budden, David, Hutter, Marcus, Veness, Joel

“…Human intelligence is characterized not only by the capacity to learn complex skills, but the ability to rapidly adapt and acquire new skills within an…”
Get full text

Online Learning in Contextual Bandits using Gated Linear Networks by Sezener, Eren, Hutter, Marcus, Budden, David, Wang, Jianan, Veness, Joel

“…We introduce a new and completely online contextual bandit algorithm called Gated Linear Contextual Bandits (GLCB). This algorithm is based on Gated Linear…”
Get full text

Gaussian Gated Linear Networks by Budden, David, Marblestone, Adam, Sezener, Eren, Lattimore, Tor, Wayne, Greg, Veness, Joel

“…We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Instead of using…”
Get full text

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models by Liška, Adam, Kočiský, Tomáš, Gribovskaya, Elena, Terzi, Tayfun, Sezener, Eren, Agrawal, Devang, d'Autume, Cyprien de Masson, Scholtes, Tim, Zaheer, Manzil, Young, Susannah, Gilsenan-McMahon, Ellen, Austin, Sophia, Blunsom, Phil, Lazaridou, Angeliki

“…Knowledge and language understanding of models evaluated through question answering (QA) has been usually studied on static snapshots of knowledge, like…”
Get full text

Large-scale multilingual audio visual dubbing by Yang, Yi, Shillingford, Brendan, Assael, Yannis, Wang, Miaosen, Liu, Wendi, Chen, Yutian, Zhang, Yu, Sezener, Eren, Cobo, Luis C, Denil, Misha, Aytar, Yusuf, de Freitas, Nando

“…We describe a system for large-scale audiovisual translation and dubbing, which translates videos from one language to another. The source language's speech…”
Get full text

Gated Linear Networks by Veness, Joel, Lattimore, Tor, Budden, David, Bhoopchand, Avishkar, Mattern, Christopher, Grabska-Barwinska, Agnieszka, Sezener, Eren, Wang, Jianan, Toth, Peter, Schmitt, Simon, Hutter, Marcus

“…This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural…”
Get full text

Behaviour Suite for Reinforcement Learning by Osband, Ian, Doron, Yotam, Hessel, Matteo, Aslanides, John, Sezener, Eren, Saraiva, Andre, McKinney, Katrina, Lattimore, Tor, Szepesvari, Csaba, Singh, Satinder, Van Roy, Benjamin, Sutton, Richard, Silver, David, Van Hasselt, Hado

“…This paper introduces the Behaviour Suite for Reinforcement Learning, or bsuite for short. bsuite is a collection of carefully-designed experiments that…”
Get full text

Computing the Value of Computation for Planning by Sezener, Can Eren

“…An intelligent agent performs actions in order to achieve its goals. Such actions can either be externally directed, such as opening a door, or internally…”
Get full text

Heuristic algorithms for obtaining Polynomial Threshold Functions with low densities by Sezener, Can Eren, Oztop, Erhan

“…In this paper we present several heuristic algorithms, including a Genetic Algorithm (GA), for obtaining polynomial threshold function (PTF) representations of…”
Get full text