The AmiCa Library In the first versions of the benchmark, a transmission con-trol protocol (TCP) interface for controllers was provided so that controller's written in other languages than Java could be interfaced to the code. However, this TCP interface introduced a considerable communication overhead making non-Java agents orders of magnitude slower, and had occasional stability issues.For later releases, a new library called AmiCo was developed for communication between the benchmark and agents developed in other language.TheAmiColibrary is applicable for interlanguage process communication beyond the Mario AI benchmark. The purpose of the library is to provide an easy-to-use and as seamless as possible bridge between foreign programming languages pre-serving high performance, comparable to the native languages’