SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.03984 · 2018

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
nickleomartin/emergent_comm_rl pwc_unofficial 0 of 3
FunctionStatusWhere it lives
action_distribution Not yet run nickleomartin/emergent_comm_rl/evaluation.py
code served (permissive licence) · get_code("5ac8a5b08cde956e")
levenshtein_message_distance Not yet run nickleomartin/emergent_comm_rl/evaluation.py
code served (permissive licence) · get_code("94b8d60180371c7b")
task_accuracy_metrics Not yet run nickleomartin/emergent_comm_rl/evaluation.py
code served (permissive licence) · get_code("70f01f07aa8bb12b")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1804.03984")
get_code_for_paper("1804.03984")
have("1804.03984")

Connect an agent — have() is free.