A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
- Marc Lanctot, V. Zambaldi, T. Graepel
- Computer ScienceNIPS
- 2 November 2017
An algorithm is described, based on approximate best responses to mixtures of policies generated using deep reinforcement learning, and empirical game-theoretic analysis to compute meta-strategies for policy selection, which generalizes previous ones such as InRL.
The LAMBADA dataset: Word prediction requiring a broad discourse context
- Denis Paperno, Germán Kruszewski, R. Fernández
- Computer ScienceAnnual Meeting of the Association for…
- 20 June 2016
It is shown that LAMBADA exemplifies a wide range of linguistic phenomena, and that none of several state-of-the-art language models reaches accuracy above 1% on this novel benchmark.
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
- Angeliki Lazaridou, K. Hermann, K. Tuyls, S. Clark
- Computer ScienceInternational Conference on Learning…
- 15 February 2018
It is found that the degree of structure found in the input data affects the nature of the emerged protocols, and thereby corroborate the hypothesis that structured compositional language is most likely to emerge when agents perceive the world as being structured.
Multi-Agent Cooperation and the Emergence of (Natural) Language
- Angeliki Lazaridou, A. Peysakhovich, Marco Baroni
- Computer ScienceInternational Conference on Learning…
- 4 November 2016
It is shown that two networks with simple configurations are able to learn to coordinate in the referential game and how to make changes to the game environment to cause the "word meanings" induced in the game to better reflect intuitive semantic properties of the images.
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
- Jack W. Rae, Sebastian Borgeaud, Geoffrey Irving
- Computer ScienceArXiv
- 8 December 2021
This paper presents an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher.
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
- Natasha Jaques, Angeliki Lazaridou, N. D. Freitas
- Computer ScienceInternational Conference on Machine Learning
- 19 October 2018
Empirical results demonstrate that influence leads to enhanced coordination and communication in challenging social dilemma environments, dramatically increasing the learning curves of the deep RL agents, and leading to more meaningful learned communication protocols.
Combining Language and Vision with a Multimodal Skip-gram Model
- Angeliki Lazaridou, N. Pham, Marco Baroni
- Computer ScienceNorth American Chapter of the Association for…
- 12 January 2015
Since they propagate visual information to all words, the MMSKIP-GRAM models discover intriguing visual properties of abstract words, paving the way to realistic implementations of embodied theories of meaning.
Experience Grounds Language
- Yonatan Bisk, Ari Holtzman, Joseph P. Turian
- Computer ScienceConference on Empirical Methods in Natural…
- 21 April 2020
It is posited that the present success of representation learning approaches trained on large text corpora can be deeply enriched from the parallel tradition of research on the contextual and social nature of language.
Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics
- Angeliki Lazaridou, M. Marelli, Roberto Zamparelli, Marco Baroni
- Computer Science, LinguisticsAnnual Meeting of the Association for…
- 1 August 2013
This work adapts compositional methods originally developed for phrases to the task of deriving the distributional meaning of morphologically complex words from their parts, and demonstrates the usefulness of a compositional morphology component in distributional semantics.
Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning
- Angeliki Lazaridou, Georgiana Dinu, Marco Baroni
- Computer ScienceAnnual Meeting of the Association for…
- 1 July 2015
This paper explores some general properties, both theoretical and empirical, of the cross-space mapping function, and builds on them to propose better methods to estimate it, and achieves large improvements over the state of the art, both in cross-linguistic and cross-modal zero-shot experiments.
...
...