356 citations · 585 across the 14 of their papers we have counts for
15 papers
Optimizing Sparse Outcomes Through Dense Behavioral Signals via Value-Guided Preference Distillation
Ziyi Zhu, Daniel R. Cahn, Thomas D. Hull +4
Aligning multi-turn dialogue agents is usually framed as matching turn-level human preferences, yet direct optimization of long-term outcomes is often ineffective and prone to rewa…
Large-Scale Retrieval for Reinforcement Learning
Peter C. Humphreys, Arthur Guez, Olivier Tieleman +3
Effective decision making involves flexibly relating past experiences and relevant contextual information to a novel situation. In deep reinforcement learning (RL), the dominant pa…
Formalising Concepts as Grounded Abstractions
Stephen Clark, Alexander Lerchner, Tamara von Glehn +4
The notion of concept has been studied for centuries, by philosophers, linguists, cognitive scientists, and researchers in artificial intelligence (Margolis & Laurence, 1999). Ther…
Grounded Language Learning Fast and Slow
Felix Hill, Olivier Tieleman, Tamara von Glehn +3
Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot…
Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning
Angeliki Lazaridou, Anna Potapenko, Olivier Tieleman
We present a method for combining multi-agent communication and traditional data-driven approaches to natural language learning, with an end goal of teaching agents to communicate…
Never Give Up: Learning Directed Exploration Strategies
Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi +8
We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic rewa…
Shaping representations through communication: community size effect in artificial learning systems
Olivier Tieleman, Angeliki Lazaridou, Shibl Mourad +2
Motivated by theories of language and communication that explain why communities with large numbers of speakers have, on average, simpler languages with more regularity, we cast th…
A Factorial Mixture Prior for Compositional Deep Generative Models
Ulrich Paquet, Sumedh K. Ghaisas, Olivier Tieleman
We assume that a high-dimensional datum, like an image, is a compositional expression of a set of properties, with a complicated non-linear relationship between the datum and its p…
Chaoticity without thermalisation in disordered lattices
O. Tieleman, Ch. Skokos, A. Lazarides
We study chaoticity and thermalization in Bose-Einstein condensates in disordered lattices, described by the discrete nonlinear Schrödinger equation (DNLS). A symplectic integratio…
Non-Abelian gauge fields and topological insulators in shaken optical lattices
Philipp Hauke, Olivier Tieleman, Alessio Celi +8
Time-periodic driving like lattice shaking offers a low-demanding method to generate artificial gauge fields in optical lattices. We identify the relevant symmetries that have to b…
Finite-momentum Bose-Einstein condensates in shaken 2D square optical lattices
M. Di Liberto, O. Tieleman, V. Branchina +1
We consider ultracold bosons in a 2D square optical lattice described by the Bose-Hubbard model. In addition, an external time-dependent sinusoidal force is applied to the system,…
Strongly interacting bosons in a 1D optical lattice at incommensurate densities
Achilleas Lazarides, Olivier Tieleman, Cristiane Morais Smith
We investigate quantum phase transitions occurring in a system of strongly interacting ultracold bosons in a 1D optical lattice. After discussing the commensurate-incommensurate tr…
Supersolid phases of dipolar bosons in optical lattices with a staggered flux
O. Tieleman, A. Lazarides, C. Morais Smith
We present the theoretical mean-field zero-temperature phase diagram of a Bose-Einstein condensate (BEC) with dipolar interactions loaded into an optical lattice with a staggered f…
Bilayer quantum Hall system at : pseudospin models and in-plane magnetic field
O. Tieleman, A. Lazarides, D. Makogon +1
We investigate two theoretical pseudomagnon-based models for a bilayer quantum Hall system (BQHS) at total filling factor . We find a unifying framework which elucidates t…
Pokrovsky-Talapov Model at finite temperature: a renormalization-group analysis
A. Lazarides, O. Tieleman, C. Morais Smith
We calculate the finite-temperature shift of the critical wavevector of the Pokrovsky-Talapov model using a renormalization-group analysis. Separating the Hamiltonian into…