A Practical Guide to Studying Emergent Communication through Grounded Language Games

This web demonstration accompanies the following paper:

Nevens J., Van Eecke, P. and Beuls K. A Practical Guide to Studying Emergent Communication through Grounded Language Games (2019), AISB 19, Falmouth.

Abstract

The question of how an effective and efficient communication system can emerge in a population of agents that need to solve a particular task attracts more and more attention from researchers in many fields, including artificial intelligence, linguistics and statistical physics. A common methodology for studying this question consists of carrying out multi-agent experiments in which a population of agents takes part in a series of scripted and task-oriented communicative interactions, called ‘language games’. While each individual language game is typically played by two agents in the population, a large series of games allows the population to converge on a shared communication system. Setting up an experiment in which a rich system for communicating about the real world emerges is a major enterprise; as it requires a variety of software components for running multi-agent experiments, for interacting with sensors and actuators, for conceptualising and interpreting semantic structures, and for mapping between these semantic structures and linguistic utterances. The aim of this paper is twofold. On the one hand, it introduces a high-level robot interface that extends the Babel software system, presenting for the first time a toolkit that provides flexible modules for dealing with each subtask involved in running advanced grounded language game experiments. On the other hand, it provides a practical guide to using the toolkit for implementing such experiments, taking a grounded colour naming game experiment as a didactic example.

The Experiment

The goal of the colour naming game experiment is to show how a shared communication system for referring to objects by their colour can emerge in a population of autonomous agents. The agents start without any concepts or words, perceiving only the average colour values of the objects in the scene. In a real-world setting, transmitting raw sensor values does not lead to successful communication, because the sensors of each agent will always record slightly different values due to differences in the agents’ perspectives on the scene, changes in lighting conditions and in some cases differences in robot morphology. Therefore, concepts and words form the necessary layers to abstract away from sensor data, in order to achieve more robust communication.

In essence, the emergence of colour categories and words through self-organisation can be achieved by the agents dividing their continuous colour space into convex regions that correspond to colour categories that are functional in the world, and by establishing a shared lexicon to refer to each region. An operationalisation of this solution has been proposed in the form of the grounded colour naming game experiment.

Web Demonstration

This web demonstration shows the result of running the grounded colour naming game experiment. The experiment was ran for 1000 interactions, of which every 100th interaction is shown below. The following parameter values were used to generate this demonstration:

Parameter Value
Number of agents 10
Min. context size 2
Max. context size 5
Perceptual deviation No
Mode Simulation

Jump to:


Interaction 1


Agent 6 is the speaker

Agent 1 is the hearer

Running in simulation mode


Processed scene:
lab = (85.50, -74.84, -19.40)
sensory-object
lab = (66.66, 104.42, -51.89)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-2 as the topic

The speaker tries to conceptualise the topic

Conceptualisation failed

A new color category is created

lab = (66.66, 104.42, -51.89)
color-category

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-1

lab = (66.66, 104.42, -51.89)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-1)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-1source-set-1color-category-2)struct1(get-contextsource-set-1)struct0:SOURCEdashSETdash11->struct1:SOURCEdashSETdash12struct2(bindcolor-categorycolor-category-2color-category-1)struct0:COLORdashCATEGORYdash21->struct2:COLORdashCATEGORYdash23

Applying
in formulation


initial structure
application process
constructional dependencies
g
applied constructions
resulting structure

Utterance: ""

Formulation failed

A new construction is created

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-2source-set-2color-category-3)struct1(get-contextsource-set-2)struct0:SOURCEdashSETdash21->struct1:SOURCEdashSETdash22struct2(bindcolor-categorycolor-category-3color-category-1)struct0:COLORdashCATEGORYdash31->struct2:COLORdashCATEGORYdash33

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_bipura_cxn0 bipura-cxnbipura_cxn0_BIPURA_UNIT_3?bipura-unit
applied constructions
resulting structure

Utterance: "bipura"

Formulation succeeded

The speaker utters the word "bipura"


The utterance "bipura" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "bipura"


Applying
in comprehension


initial structure
application process
constructional dependencies
g
applied constructions
resulting structure

Meaning:

g

Parsing failed

The hearer does not know the word "bipura"


The speaker started alignment

The speaker finished alignment


The hearer started alignment

The hearer will learn a new word

The hearer looks for a discriminating color category

The hearer could not find a discriminating category

A new color category is created

lab = (66.66, 104.42, -51.89)
color-category

The hearer adopted a new word

The hearer finished alignment


Interaction failed

The speaker's lexicon after 1 interactions:

gcluster_cluster6agent 6 (interaction 1)colour1bipura (0.5)

The hearer's lexicon after 1 interactions:

gcluster_cluster1agent 1 (interaction 1)colour1bipura (0.5)
Jump to top

Interaction 100


Agent 2 is the speaker

Agent 9 is the hearer

Running in simulation mode


Processed scene:
lab = (83.02, -137.58, 90.57)
sensory-object
lab = (94.49, -16.24, 103.07)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-357 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-137

lab = (95.26, -33.94, 103.51)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-137)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-125source-set-125color-category-174)struct1(get-contextsource-set-125)struct0:SOURCEdashSETdash1251->struct1:SOURCEdashSETdash1252struct2(bindcolor-categorycolor-category-174color-category-137)struct0:COLORdashCATEGORYdash1741->struct2:COLORdashCATEGORYdash1743

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_dufami_cxn0 dufami-cxndufami_cxn0_DUFAMI_UNIT_244?dufami-unit
applied constructions
resulting structure

Utterance: "dufami"

Formulation succeeded

The speaker utters the word "dufami"


The utterance "dufami" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "dufami"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_dufami_cxn0 dufami-cxndufami_cxn0_DUFAMI_UNIT_246?dufami-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-1446?source-set-479?color-category-479)struct1(get-context?source-set-479)struct0:varSOURCEdashSETdash4791->struct1:varSOURCEdashSETdash4792struct2(bindcolor-category?color-category-479color-category-5)struct0:varCOLORdashCATEGORYdash4791->struct2:varCOLORdashCATEGORYdash4793

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-1446?source-set-479?color-category-479)struct1(get-context?source-set-479)struct0:varSOURCEdashSETdash4791->struct1:varSOURCEdashSETdash4792struct2(bindcolor-category?color-category-479color-category-5)struct0:varCOLORdashCATEGORYdash4791->struct2:varCOLORdashCATEGORYdash4793

The hearer tries to interpret the utterance using COLOR-CATEGORY-5

lab = (91.64, -50.28, 99.86)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-357 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-137

The agent rewarded the construction:

The agent punished the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-5

The agent rewarded the construction:

The agent punished the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 100 interactions:

gcluster_cluster2agent 2 (interaction 100)colour1fedawa (0.5)colour2bipura (0.4)colour3dozize (0.4)colour4dufami (0.7) pupibe (0.3)

The hearer's lexicon after 100 interactions:

gcluster_cluster9agent 9 (interaction 100)colour1sakalu (0.4)colour2bipura (0.5)colour3lokolo (0.5) vapufo (0.5)colour4dufami (0.9) pikono (0.4)
Jump to top

Interaction 200


Agent 6 is the speaker

Agent 1 is the hearer

Running in simulation mode


Processed scene:
lab = (96.69, -22.51, 105.00)
sensory-object
lab = (61.20, 89.30, 74.92)
sensory-object
lab = (80.72, -134.32, 88.16)
sensory-object
lab = (66.85, 104.60, -51.56)
sensory-object
lab = (86.58, -81.11, -16.63)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-695 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-237

lab = (80.43, -133.97, 88.20)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-237)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-232source-set-232color-category-290)struct1(get-contextsource-set-232)struct0:SOURCEdashSETdash2321->struct1:SOURCEdashSETdash2322struct2(bindcolor-categorycolor-category-290color-category-237)struct0:COLORdashCATEGORYdash2901->struct2:COLORdashCATEGORYdash2903

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_salela_cxn0 salela-cxnsalela_cxn0_SALELA_UNIT_51?salela-unit
applied constructions
resulting structure

Utterance: "salela"

Formulation succeeded

The speaker utters the word "salela"


The utterance "salela" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "salela"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_salela_cxn0 salela-cxnsalela_cxn0_SALELA_UNIT_53?salela-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-3995?context-2870?x-2989)struct1(get-context?context-2870)struct0:varCONTEXTdash28701->struct1:varCONTEXTdash28702struct2(bindcolor-category?x-2989color-category-74)struct0:varXdash29891->struct2:varXdash29893

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-3995?context-2870?x-2989)struct1(get-context?context-2870)struct0:varCONTEXTdash28701->struct1:varCONTEXTdash28702struct2(bindcolor-category?x-2989color-category-74)struct0:varXdash29891->struct2:varXdash29893

The hearer tries to interpret the utterance using COLOR-CATEGORY-74

lab = (83.02, -137.58, 90.57)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-695 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-237

The agent rewarded the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-74

The agent rewarded the construction:

The agent punished the construction:

The agent punished the construction:

The agent punished the construction:

The agent punished the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 200 interactions:

gcluster_cluster6agent 6 (interaction 200)colour1xuxixi (0.7) sakalu (0.5) ziwomo (0.3) sudexo (0.3) xotosu (0.3)colour2zuvoba (0.6) fufiki (0.3)colour3bipura (0.8) xeluwi (0.3)colour4salela (0.5)colour5dozize (0.6) puwaso (0.4) buboga (0.4)colour6dufami (0.7)

The hearer's lexicon after 200 interactions:

gcluster_cluster1agent 1 (interaction 200)colour1sudexo (0.6) fefape (0.5) sakalu (0.5) ziwomo (0.5)colour2fufiki (0.5) dufami (0.5) muzazu (0.3) rimixa (0.3)colour3bipura (0.9) nuvani (0.3)colour4salela (0.6) letave (0.4) tuxipi (0.4) mozave (0.4) zovune (0.4)colour5buboga (0.6) puwaso (0.2)
Jump to top

Interaction 300


Agent 0 is the speaker

Agent 3 is the hearer

Running in simulation mode


Processed scene:
lab = (81.30, -135.12, 89.00)
sensory-object
lab = (84.44, -72.34, -21.24)
sensory-object
lab = (60.53, 88.53, 74.28)
sensory-object
lab = (32.41, 79.38, -108.12)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-1027 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-110

lab = (59.84, 87.71, 73.57)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-110)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-333source-set-333color-category-392)struct1(get-contextsource-set-333)struct0:SOURCEdashSETdash3331->struct1:SOURCEdashSETdash3332struct2(bindcolor-categorycolor-category-392color-category-110)struct0:COLORdashCATEGORYdash3921->struct2:COLORdashCATEGORYdash3923

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_muzazu_cxn0 muzazu-cxnmuzazu_cxn0_MUZAZU_UNIT_374?muzazu-unit
applied constructions
resulting structure

Utterance: "muzazu"

Formulation succeeded

The speaker utters the word "muzazu"


The utterance "muzazu" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "muzazu"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_muzazu_cxn0 muzazu-cxnmuzazu_cxn0_MUZAZU_UNIT_376?muzazu-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-6996?context-5230?x-5378)struct1(get-context?context-5230)struct0:varCONTEXTdash52301->struct1:varCONTEXTdash52302struct2(bindcolor-category?x-5378color-category-73)struct0:varXdash53781->struct2:varXdash53783

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-6996?context-5230?x-5378)struct1(get-context?context-5230)struct0:varCONTEXTdash52301->struct1:varCONTEXTdash52302struct2(bindcolor-category?x-5378color-category-73)struct0:varXdash53781->struct2:varXdash53783

The hearer tries to interpret the utterance using COLOR-CATEGORY-73

lab = (60.87, 88.91, 74.52)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-1027 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-110

The agent rewarded the construction:

The agent punished the construction:

The agent punished the construction:

The agent punished the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-73

The agent rewarded the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 300 interactions:

gcluster_cluster0agent 0 (interaction 300)colour1xuxixi (0.8) fefape (0.1) ziwomo (0.1) sakalu (0.1) sudexo (0.1)colour2muzazu (0.7) fufiki (0.4) zuvoba (0.2) duvuzo (0.2)colour3bipura (0.5) xeluwi (0.2) nuvani (0.2)colour4gomudo (0.5) tuxipi (0.5) zovune (0.5) pikono (0.4) letave (0.4) salela (0.3)colour5vapufo (0.3)colour6dufami (1.0)

The hearer's lexicon after 300 interactions:

gcluster_cluster3agent 3 (interaction 300)colour1xuxixi (0.5) ziwomo (0.1)colour2muzazu (1.0)colour3mufume (0.5) bipura (0.4)colour4gomudo (0.5) mozave (0.5) tuxipi (0.1)colour5buboga (1.0) puwaso (0.5) vapufo (0.3)colour6dufami (1.0)
Jump to top

Interaction 400


Agent 6 is the speaker

Agent 3 is the hearer

Running in simulation mode


Processed scene:
lab = (81.58, -135.58, 89.22)
sensory-object
lab = (85.51, -74.81, -19.39)
sensory-object
lab = (61.20, 89.30, 74.93)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-1380 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-19

lab = (86.52, -77.25, -17.65)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-19)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-433source-set-433color-category-492)struct1(get-contextsource-set-433)struct0:SOURCEdashSETdash4331->struct1:SOURCEdashSETdash4332struct2(bindcolor-categorycolor-category-492color-category-19)struct0:COLORdashCATEGORYdash4921->struct2:COLORdashCATEGORYdash4923

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_buboga_cxn0 buboga-cxnbuboga_cxn0_BUBOGA_UNIT_576?buboga-unit
applied constructions
resulting structure

Utterance: "buboga"

Formulation succeeded

The speaker utters the word "buboga"


The utterance "buboga" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "buboga"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_buboga_cxn0 buboga-cxnbuboga_cxn0_BUBOGA_UNIT_578?buboga-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-10017?source-set-2286?color-category-2286)struct1(get-context?source-set-2286)struct0:varSOURCEdashSETdash22861->struct1:varSOURCEdashSETdash22862struct2(bindcolor-category?color-category-2286color-category-64)struct0:varCOLORdashCATEGORYdash22861->struct2:varCOLORdashCATEGORYdash22863

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-10017?source-set-2286?color-category-2286)struct1(get-context?source-set-2286)struct0:varSOURCEdashSETdash22861->struct1:varSOURCEdashSETdash22862struct2(bindcolor-category?color-category-2286color-category-64)struct0:varCOLORdashCATEGORYdash22861->struct2:varCOLORdashCATEGORYdash22863

The hearer tries to interpret the utterance using COLOR-CATEGORY-64

lab = (86.49, -77.91, -17.53)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-1380 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-19

The agent rewarded the construction:

The agent punished the construction:

The agent punished the construction:

The agent punished the construction:


Removed  
from  


Removed  
from  

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-64

The agent rewarded the construction:

The agent punished the construction:

The agent punished the construction:


Removed  
from  


Removed  
from  

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 400 interactions:

gcluster_cluster6agent 6 (interaction 400)colour1xuxixi (0.4) sakalu (0.3) ziwomo (0.1)colour2zuvoba (0.7) muzazu (0.5) fufiki (0.1)colour3bipura (1.0)colour4gomudo (0.7) salela (0.2) tuxipi (0.2)colour5buboga (0.8) vapufo (0.4) dozize (0.2)colour6dufami (1.0)

The hearer's lexicon after 400 interactions:

gcluster_cluster3agent 3 (interaction 400)colour1sakalu (0.7) xuxixi (0.3)colour2muzazu (1.0)colour3bipura (0.5) mufume (0.3)colour4gomudo (0.7) mozave (0.2)colour5buboga (1.0) puwaso (0.2)colour6dufami (1.0)
Jump to top

Interaction 500


Agent 3 is the speaker

Agent 8 is the hearer

Running in simulation mode


Processed scene:
lab = (61.24, 89.18, 74.96)
sensory-object
lab = (95.52, -25.21, 103.85)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-1718 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-73

lab = (60.62, 88.59, 74.30)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-73)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-533source-set-533color-category-592)struct1(get-contextsource-set-533)struct0:SOURCEdashSETdash5331->struct1:SOURCEdashSETdash5332struct2(bindcolor-categorycolor-category-592color-category-73)struct0:COLORdashCATEGORYdash5921->struct2:COLORdashCATEGORYdash5923

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_muzazu_cxn0 muzazu-cxnmuzazu_cxn0_MUZAZU_UNIT_798?muzazu-unit
applied constructions
resulting structure

Utterance: "muzazu"

Formulation succeeded

The speaker utters the word "muzazu"


The utterance "muzazu" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "muzazu"


Applying
in comprehension


initial structure
application process
constructional dependencies
g
applied constructions
resulting structure

Meaning:

g

Parsing failed

The hearer does not know the word "muzazu"


The speaker started alignment

The agent punished the construction:

The speaker finished alignment


The hearer started alignment

The hearer will learn a new word

The hearer looks for a discriminating color category

The hearer found a discriminating category

lab = (61.03, 89.07, 74.66)
color-category

The hearer adopted a new word

The hearer finished alignment


Interaction failed

The speaker's lexicon after 500 interactions:

gcluster_cluster3agent 3 (interaction 500)colour1sakalu (0.9) xuxixi (0.1)colour2muzazu (0.9)colour3bipura (0.9)colour4gomudo (0.8) mozave (0.1)colour5buboga (1.0)colour6dufami (1.0)

The hearer's lexicon after 500 interactions:

gcluster_cluster8agent 8 (interaction 500)colour1sakalu (1.0)colour2zuvoba (1.0) muzazu (0.5)colour3bipura (1.0)colour4gomudo (1.0) tuxipi (0.2)colour5buboga (1.0)colour6dufami (1.0)
Jump to top

Interaction 600


Agent 6 is the speaker

Agent 0 is the hearer

Running in simulation mode


Processed scene:
lab = (32.84, 80.07, -109.07)
sensory-object
lab = (94.93, -17.50, 103.46)
sensory-object
lab = (67.24, 104.97, -50.90)
sensory-object
lab = (83.02, -137.58, 90.57)
sensory-object
lab = (86.70, -79.54, -17.33)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-2057 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-84

lab = (32.42, 79.32, -108.06)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-84)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-633source-set-633color-category-693)struct1(get-contextsource-set-633)struct0:SOURCEdashSETdash6331->struct1:SOURCEdashSETdash6332struct2(bindcolor-categorycolor-category-693color-category-84)struct0:COLORdashCATEGORYdash6931->struct2:COLORdashCATEGORYdash6933

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_sakalu_cxn0 sakalu-cxnsakalu_cxn0_SAKALU_UNIT_1025?sakalu-unit
applied constructions
resulting structure

Utterance: "sakalu"

Formulation succeeded

The speaker utters the word "sakalu"


The utterance "sakalu" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "sakalu"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_sakalu_cxn0 sakalu-cxnsakalu_cxn0_SAKALU_UNIT_1027?sakalu-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-14362?context-11576?x-11762)struct1(get-context?context-11576)struct0:varCONTEXTdash115761->struct1:varCONTEXTdash115762struct2(bindcolor-category?x-11762color-category-56)struct0:varXdash117621->struct2:varXdash117623

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-14362?context-11576?x-11762)struct1(get-context?context-11576)struct0:varCONTEXTdash115761->struct1:varCONTEXTdash115762struct2(bindcolor-category?x-11762color-category-56)struct0:varXdash117621->struct2:varXdash117623

The hearer tries to interpret the utterance using COLOR-CATEGORY-56

lab = (32.15, 78.82, -107.43)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-2057 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-84

The agent rewarded the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-56

The agent rewarded the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 600 interactions:

gcluster_cluster6agent 6 (interaction 600)colour1sakalu (1.0)colour2zuvoba (0.5) muzazu (0.4)colour3bipura (1.0)colour4gomudo (0.7) salela (0.2)colour5buboga (1.0)colour6dufami (1.0)

The hearer's lexicon after 600 interactions:

gcluster_cluster0agent 0 (interaction 600)colour1sakalu (1.0)colour2muzazu (1.0) zuvoba (0.2)colour3bipura (1.0)colour4salela (0.4) gomudo (0.1)colour5buboga (1.0)colour6dufami (1.0)
Jump to top

Interaction 700


Agent 4 is the speaker

Agent 8 is the hearer

Running in simulation mode


Processed scene:
lab = (66.95, 104.25, -48.70)
sensory-object
lab = (82.16, -136.36, 89.78)
sensory-object
lab = (32.74, 79.80, -108.69)
sensory-object
lab = (61.25, 89.15, 74.97)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-2410 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-192

lab = (66.86, 104.32, -49.99)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-192)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-733source-set-733color-category-793)struct1(get-contextsource-set-733)struct0:SOURCEdashSETdash7331->struct1:SOURCEdashSETdash7332struct2(bindcolor-categorycolor-category-793color-category-192)struct0:COLORdashCATEGORYdash7931->struct2:COLORdashCATEGORYdash7933

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_bipura_cxn0 bipura-cxnbipura_cxn0_BIPURA_UNIT_1520?bipura-unit
applied constructions
resulting structure

Utterance: "bipura"

Formulation succeeded

The speaker utters the word "bipura"


The utterance "bipura" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "bipura"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_bipura_cxn0 bipura-cxnbipura_cxn0_BIPURA_UNIT_1522?bipura-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-16082?context-13137?x-13328)struct1(get-context?context-13137)struct0:varCONTEXTdash131371->struct1:varCONTEXTdash131372struct2(bindcolor-category?x-13328color-category-15)struct0:varXdash133281->struct2:varXdash133283

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-16082?context-13137?x-13328)struct1(get-context?context-13137)struct0:varCONTEXTdash131371->struct1:varCONTEXTdash131372struct2(bindcolor-category?x-13328color-category-15)struct0:varXdash133281->struct2:varXdash133283

The hearer tries to interpret the utterance using COLOR-CATEGORY-15

lab = (66.50, 104.07, -51.17)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-2410 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-192

The agent rewarded the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-15

The agent rewarded the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 700 interactions:

gcluster_cluster4agent 4 (interaction 700)colour1sakalu (1.0)colour2muzazu (1.0) zuvoba (0.2)colour3bipura (1.0)colour4gomudo (1.0) salela (0.5)colour5buboga (1.0)colour6dufami (1.0)

The hearer's lexicon after 700 interactions:

gcluster_cluster8agent 8 (interaction 700)colour1sakalu (1.0)colour2muzazu (0.7) zuvoba (0.7)colour3bipura (1.0)colour4gomudo (0.8) salela (0.6)colour5buboga (1.0)colour6dufami (1.0)
Jump to top

Interaction 800


Agent 2 is the speaker

Agent 8 is the hearer

Running in simulation mode


Processed scene:
lab = (85.24, -74.20, -19.85)
sensory-object
lab = (81.01, -134.73, 88.49)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-2758 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-209

lab = (82.02, -136.11, 89.62)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-209)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-833source-set-833color-category-893)struct1(get-contextsource-set-833)struct0:SOURCEdashSETdash8331->struct1:SOURCEdashSETdash8332struct2(bindcolor-categorycolor-category-893color-category-209)struct0:COLORdashCATEGORYdash8931->struct2:COLORdashCATEGORYdash8933

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_salela_cxn0 salela-cxnsalela_cxn0_SALELA_UNIT_1116?salela-unit
applied constructions
resulting structure

Utterance: "salela"

Formulation succeeded

The speaker utters the word "salela"


The utterance "salela" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "salela"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_salela_cxn0 salela-cxnsalela_cxn0_SALELA_UNIT_1118?salela-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-17755?context-14638?x-14833)struct1(get-context?context-14638)struct0:varCONTEXTdash146381->struct1:varCONTEXTdash146382struct2(bindcolor-category?x-14833color-category-77)struct0:varXdash148331->struct2:varXdash148333

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-17755?context-14638?x-14833)struct1(get-context?context-14638)struct0:varCONTEXTdash146381->struct1:varCONTEXTdash146382struct2(bindcolor-category?x-14833color-category-77)struct0:varXdash148331->struct2:varXdash148333

The hearer tries to interpret the utterance using COLOR-CATEGORY-77

lab = (82.55, -136.91, 90.11)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-2758 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-209

The agent rewarded the construction:

The agent punished the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-77

The agent rewarded the construction:

The agent punished the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 800 interactions:

gcluster_cluster2agent 2 (interaction 800)colour1sakalu (1.0)colour2muzazu (1.0) zuvoba (0.5)colour3bipura (1.0)colour4salela (1.0) gomudo (0.4)colour5buboga (1.0)colour6dufami (1.0)

The hearer's lexicon after 800 interactions:

gcluster_cluster8agent 8 (interaction 800)colour1sakalu (1.0)colour2muzazu (0.9) zuvoba (0.5)colour3bipura (1.0)colour4salela (1.0) gomudo (0.4)colour5buboga (1.0)colour6dufami (1.0)
Jump to top

Interaction 900


Agent 8 is the speaker

Agent 5 is the hearer

Running in simulation mode


Processed scene:
lab = (83.03, -137.43, 90.58)
sensory-object
lab = (86.83, -77.93, -17.11)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-3118 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-77

lab = (82.52, -136.83, 90.04)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-77)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-933source-set-933color-category-993)struct1(get-contextsource-set-933)struct0:SOURCEdashSETdash9331->struct1:SOURCEdashSETdash9332struct2(bindcolor-categorycolor-category-993color-category-77)struct0:COLORdashCATEGORYdash9931->struct2:COLORdashCATEGORYdash9933

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_salela_cxn0 salela-cxnsalela_cxn0_SALELA_UNIT_1350?salela-unit
applied constructions
resulting structure

Utterance: "salela"

Formulation succeeded

The speaker utters the word "salela"


The utterance "salela" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "salela"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_salela_cxn0 salela-cxnsalela_cxn0_SALELA_UNIT_1352?salela-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-19337?context-16059?x-16255)struct1(get-context?context-16059)struct0:varCONTEXTdash160591->struct1:varCONTEXTdash160592struct2(bindcolor-category?x-16255color-category-232)struct0:varXdash162551->struct2:varXdash162553

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-19337?context-16059?x-16255)struct1(get-context?context-16059)struct0:varCONTEXTdash160591->struct1:varCONTEXTdash160592struct2(bindcolor-category?x-16255color-category-232)struct0:varXdash162551->struct2:varXdash162553

The hearer tries to interpret the utterance using COLOR-CATEGORY-232

lab = (82.49, -136.74, 89.99)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-3118 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-77

The agent rewarded the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-232

The agent rewarded the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 900 interactions:

gcluster_cluster8agent 8 (interaction 900)colour1sakalu (1.0)colour2muzazu (1.0)colour3bipura (1.0)colour4salela (1.0)colour5buboga (1.0)colour6dufami (1.0)

The hearer's lexicon after 900 interactions:

gcluster_cluster5agent 5 (interaction 900)colour1sakalu (1.0)colour2muzazu (1.0)colour3bipura (1.0)colour4salela (1.0)colour5buboga (1.0)colour6dufami (1.0)
Jump to top

Interaction 1000


Agent 1 is the speaker

Agent 6 is the hearer

Running in simulation mode


Processed scene:
lab = (93.86, -23.12, 102.27)
sensory-object
lab = (86.03, -76.11, -18.49)
sensory-object
sensory-object-set

The speaker chooses SENSORY-OBJECT-3471 as the topic

The speaker tries to conceptualise the topic

Conceptualisation succeeded

The speaker conceptualises the topic using COLOR-CATEGORY-308

lab = (96.26, -22.57, 104.57)
color-category

Meaning representation:

gstruct0(filter-by-closest-color?topic?source-set?color-category)struct1(get-context?source-set)struct0:varSOURCEdashSET1->struct1:varSOURCEdashSET2struct2(bindcolor-category?color-categorycolor-category-308)struct0:varCOLORdashCATEGORY1->struct2:varCOLORdashCATEGORY3

The speaker tries to formulate


Formulating 

gstruct0(filter-by-closest-colortopic-1033source-set-1033color-category-1093)struct1(get-contextsource-set-1033)struct0:SOURCEdashSETdash10331->struct1:SOURCEdashSETdash10332struct2(bindcolor-categorycolor-category-1093color-category-308)struct0:COLORdashCATEGORYdash10931->struct2:COLORdashCATEGORYdash10933

Applying
in formulation


initial structure
application process
constructional dependencies
gcluster_dufami_cxn0 dufami-cxndufami_cxn0_DUFAMI_UNIT_2367?dufami-unit
applied constructions
resulting structure

Utterance: "dufami"

Formulation succeeded

The speaker utters the word "dufami"


The utterance "dufami" is passed from speaker to hearer


The hearer tries to parse the utterance


Comprehending "dufami"


Applying
in comprehension


initial structure
application process
constructional dependencies
gcluster_dufami_cxn0 dufami-cxndufami_cxn0_DUFAMI_UNIT_2369?dufami-unit
applied constructions
resulting structure

Meaning:

gstruct0(filter-by-closest-color?topic-20853?context-17422?x-17618)struct1(get-context?context-17422)struct0:varCONTEXTdash174221->struct1:varCONTEXTdash174222struct2(bindcolor-category?x-17618color-category-14)struct0:varXdash176181->struct2:varXdash176183

Parsing succeeded

The hearer could parse the utterance:

Meaning representation:

gstruct0(filter-by-closest-color?topic-20853?context-17422?x-17618)struct1(get-context?context-17422)struct0:varCONTEXTdash174221->struct1:varCONTEXTdash174222struct2(bindcolor-category?x-17618color-category-14)struct0:varXdash176181->struct2:varXdash176183

The hearer tries to interpret the utterance using COLOR-CATEGORY-14

lab = (95.75, -22.88, 104.10)
color-category

Interpretation succeeded

The hearer points to SENSORY-OBJECT-3471 as the topic

This is correct. The speaker nods


The speaker started alignment

The agent shifted COLOR-CATEGORY-308

The agent rewarded the construction:

The speaker finished alignment


The hearer started alignment

The agent shifted COLOR-CATEGORY-14

The agent rewarded the construction:

The hearer finished alignment


Interaction succeeded

The speaker's lexicon after 1000 interactions:

gcluster_cluster1agent 1 (interaction 1000)colour1sakalu (1.0)colour2muzazu (1.0)colour3bipura (1.0)colour4salela (1.0)colour5buboga (1.0)colour6dufami (1.0)

The hearer's lexicon after 1000 interactions:

gcluster_cluster6agent 6 (interaction 1000)colour1sakalu (1.0)colour2muzazu (1.0)colour3bipura (1.0)colour4salela (1.0)colour5buboga (1.0)colour6dufami (1.0)