pith. sign in

arxiv: 1804.03984 · v1 · pith:5RU53UINnew · submitted 2018-04-11 · 💻 cs.AI · cs.CL· cs.LG· cs.MA

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

classification 💻 cs.AI cs.CLcs.LGcs.MA
keywords agentscommunicationinputcompositionaldatagameslanguagelearn
0
0 comments X
read the original abstract

The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent communication tasks. Here we scale up this research by using contemporary deep learning methods and by training reinforcement-learning neural network agents on referential communication games. We extend previous work, in which agents were trained in symbolic environments, by developing agents which are able to learn from raw pixel data, a more challenging and realistic input representation. We find 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Gradient-Based Program Synthesis with Neurally Interpreted Languages

    cs.LG 2026-04 unverdicted novelty 8.0

    NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prio...

  2. Compositionality and the lexicon in evolutionary semantics

    cs.CL 2026-06 unverdicted novelty 7.0

    A co-evolutionary model of lexical meanings and composition under simplicity and accuracy pressures shows conservativity in quantifiers emerges as an efficient abstraction on the Pareto frontier.

  3. Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents

    cs.CL 2026-06 unverdicted novelty 7.0

    Agents acquire lexical labels for visual concepts following a perceptual coherence gradient where perceptual distance predicts learning accuracy independently of semantic distance in a pre-registered CIFAR-100 experiment.