SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.11871 · 2019

Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 3 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
facebookresearch/fruit-tools-game pwc_unofficial 3 of 6
FunctionStatusWhere it lives
one_hot Ran facebookresearch/fruit-tools-game/utils.py
pointer only (licence: MIT) · get_code("0c64ac267107a5dc")
return_bs_message Ran facebookresearch/fruit-tools-game/utils.py
pointer only (licence: MIT) · get_code("e9d7d35361ccb03b")
sample_stgs Ran facebookresearch/fruit-tools-game/utils.py
pointer only (licence: MIT) · get_code("7f6952c7208a1014")
create_classif_dataset_simple Not yet run facebookresearch/fruit-tools-game/semantical_analysis.py
pointer only (licence: MIT) · get_code("c52c2123819dcd3a")
sem_analysis Not yet run facebookresearch/fruit-tools-game/semantical_analysis.py
pointer only (licence: MIT) · get_code("350cae97b5683fa0")
shuffle_convers Not yet run facebookresearch/fruit-tools-game/semantical_analysis.py
pointer only (licence: MIT) · get_code("04f71369e0a8d89c")

Repositories linked to this paper

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

Abstract

Recent research studies communication emergence in communities of deep network agents assigned a joint task, hoping to gain insights on human language evolution. We propose here a new task capturing crucial aspects of the human environment, such as natural object affordances, and of human conversation, such as full symmetry among the participants. By conducting a thorough pragmatic and semantic analysis of the emergent protocol, we show that the agents solve the shared task through genuine bilateral, referential communication. However, the agents develop multiple idiolects, which makes us conclude that full symmetry is not a sufficient condition for a common language to emerge.

For agents

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

get_harvested_code_for_paper("1905.11871")
get_code_for_paper("1905.11871")
have("1905.11871")

Connect an agent — have() is free.