caa a22 4500 475800990 CHVBK 20180406123737.0 cr unu---uuuuu 170329e20000201xx s 000 0 eng 10.1023/A:1009615730125 doi (NATIONALLICENCE)springer-10.1023/A:1009615730125 Online Interactive Neuro-evolution [Elektronische Daten] [A. Agogino, K. Stanley, R. Miikkulainen] In standard neuro-evolution, a population of networks is evolved in a task, and the network that best solves the task is found. This network is then fixed and used to solve future instances of the problem. Networks evolved in this way do not handle real-time interaction very well. It is hard to evolve a solution ahead of time that can cope effectively with all the possible environments that might arise in the future and with all the possible ways someone may interact with it. This paper proposes evolving feedforward neural networks online to create agents that improve their performance through real-time interaction. This approach is demonstrated in a game world where neural-network-controlled individuals play against humans. Through evolution, these individuals learn to react to varying opponents while appropriately taking into account conflicting goals. After initial evaluation offline, the population is allowed to evolve online, and its performance improves considerably. The population not only adapts to novel situations brought about by changing strategies in the opponent and the game layout, but it also improves its performance in situations that it has already seen in offline training. This paper will describe an implementation of online evolution and shows that it is a practical method that exceeds the performance of offline evolution alone. Kluwer Academic Publishers, 2000 evolution nationallicence online nationallicence game nationallicence neural nationallicence network nationallicence genetic nationallicence real-time nationallicence Agogino A. Dept. of Computer Science, The University of Texas at Austin, TAY 2.124, C0500, 78712-1188, Austin, TX, U.S.A. aut Stanley K. Dept. of Computer Science, The University of Texas at Austin, TAY 2.124, C0500, 78712-1188, Austin, TX, U.S.A. aut Miikkulainen R. Dept. of Computer Science, The University of Texas at Austin, TAY 2.124, C0500, 78712-1188, Austin, TX, U.S.A. aut Neural Processing Letters Kluwer Academic Publishers 11/1(2000-02-01), 29-38 1370-4621 11:1<29 2000 11 11063 https://doi.org/10.1023/A:1009615730125 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1009615730125 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Agogino A. Dept. of Computer Science, The University of Texas at Austin, TAY 2.124, C0500, 78712-1188, Austin, TX, U.S.A aut NATIONALLICENCE 700 1- Stanley K. Dept. of Computer Science, The University of Texas at Austin, TAY 2.124, C0500, 78712-1188, Austin, TX, U.S.A aut NATIONALLICENCE 700 1- Miikkulainen R. Dept. of Computer Science, The University of Texas at Austin, TAY 2.124, C0500, 78712-1188, Austin, TX, U.S.A aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 11/1(2000-02-01), 29-38 1370-4621 11:1<29 2000 11 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer