Efficient communication using reinforcement learning in a cooperative navigation game

Examensarbete för masterexamen

Använd denna länk för att citera eller länka till detta dokument: https://hdl.handle.net/20.500.12380/304833
Ladda ner:
Fil Beskrivning StorlekFormat 
CSE 22-27 Bohman Rogmalm Hornestedt.pdf2.49 MBAdobe PDFVisa
Bibliografiska detaljer
FältVärde
Typ: Examensarbete för masterexamen
Titel: Efficient communication using reinforcement learning in a cooperative navigation game
Författare: Bohman, Erik
Rogmalm Hornestedt, Simon
Sammanfattning: The thesis aims to investigate if agents are able to develop an efficient communication, with semantic meanings, and solve a navigation problem, using reinforcement learning. Additionally, it aims to evaluate the relevancy and benefit of one and two-way communication in comparison to each other and no communication. The problem is tackled in a multi-agent system (two agents), using a cooperative navigation game. The agents possess different privately held information, they are hence equipped with a communication channel and a language with no initial semantic meaning to convey the information to each other and solve the task of finding a target inside an environment with distracting obstacles. The experiments take place in both a discrete and a continuous setting with a varying number of communication ways and are evaluated based on the average time to complete the navigation. It is shown in the thesis that the agents can develop a language with a semantic meaning, which contributes to an efficient communication when set in a discrete environment and in a continuous static environment. However, it is inconclusive whether there are any significant benefits to be gained from a two-way communication compared to a one-way communication and whether the task can be solved in a continuous non-static environment.
Nyckelord: machine learning;reinforcement learning;efficient communication;multiagent system
Utgivningsdatum: 2022
Utgivare: Chalmers tekniska högskola / Institutionen för data och informationsteknik
URI: https://hdl.handle.net/20.500.12380/304833
Samling:Examensarbeten för masterexamen // Master Theses



Materialet i Chalmers öppna arkiv är upphovsrättsligt skyddat och får ej användas i kommersiellt syfte!