Human-Like Combat Behaviour via Multiobjective Neuroevolution

Believable Bot Navigation via Playback of Human Traces

“…Additional details about the competition are available in previous publications by the organizer, Philip Hingston ( [4,25], and elsewhere this book [26].…”

“…The overall architecture of the bot is described in detail elsewhere in this book [26]. In the BotPrize 2010 competition, the bot uses the HTC in order to improve its navigation behavior: when the bot gets stuck while moving along a path or during combat (section 4.3), it executes actions selected by the controller.…”

“…Because it is relatively simple and does not rely on changing external human databases, the Scripted Unstuck Controller was used whenever the bot got stuck while evolving the battle controller for the UTˆ2 bot [26]. It also provides a strong benchmark for comparisons with the performance of the Human Trace Controller.…”

UT⁁2: Human-like behavior via neuroevolution of combat behavior and replay of human traces

“…This version of the bot, referred to as UTˆ2-2010 for the rest of this paper, was based on two core ideas: (1) multiobjective neuroevolution was used to learn skilled combat behavior, but filters on the available combat actions ensured that the behavior was still human-like despite being evolved for performance, and (2) a database of traces of human play was used to help the bot get unstuck when its navigation capabilities failed. UTˆ2-2010 is described in full detail in upcoming chapters [16,20] for the book Believable Bots. The UTˆ2 bot has been modified in several ways since 2010 in order to increase its humanness rating for this year's competition: Extra input features have been provided to help it evolve better combat behavior, extra filters on combat actions inject more human knowledge into the bot, the role of human traces in the navigation of the bot has been expanded, and an extra control module has been added which encourages the bot to observe other players the way a human would, rather than simply battle them.…”

“…UTˆ2 makes use of a large number of network inputs, so it is important to be able to ignore certain inputs early in evolution, when establishing a baseline policy is more important than refining the policy. The full set of inputs used by UTˆ2-2010 is described in [20], but some extra inputs added to UTˆ2 for this year's competition are described later in section III-C.…”