[vc_empty_space][vc_empty_space]
Multiagent System Development for Cooperative Multiplayer Video Game Using Deep Q-Network
Wijaya R.I.a, Maulidevi N.U.a
a School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2019 IEEE.In this work, a multiagent system was developed for cooperative multiplayer video game. One of the cooperative popular multiplayer video games when this paper is written is Overcooked 2. For that reason, the game is chosen as the development environment for this work. Because Overcooked 2 is not an open-source software and does not provide APIs for reading information and accept inputs, the built multiagent system is not applied directly to Overcooked 2. A game with similar mechanics is used to represent Overcooked 2 instead. The game has simplified display and features of the game it is based on. Agents in the system use deep q-network to decide what action to be taken. The neural network takes the game state which consist of information from the game and the coordination protocol i.e. blackboard system as inputs. The outputs of the neural network are estimated q-values of every actions. The developed system is then compared with a system where its agents choose actions randomly. Both systems played the developed game for certain amount of episodes, then the average score of the systems are compared. Based on the comparison result, the developed system has better average score.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Blackboard systems,Comparison result,Coordination protocols,Development environment,Multiagent system development,Multiplayers,System use,Video game[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]cooperative deep q-network,multiagent,multiplayer[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICAICTA.2019.8904297[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]