When building an application that requires object class recognition, having enough data to learn from is critical for good performance, and can easily determine the success or fai...
In this paper, we present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the concept of usin...
Spoken language is one of the most intuitive forms of interaction between humans and agents. Unfortunately, agents that interact with people using natural language often experienc...
In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet if game characters could ...
Kenneth O. Stanley, Igor Karpov, Risto Miikkulaine...
Abstract— Many applications require teams of robots to cooperatively execute complex tasks. Among these domains are those where successful coordination solutions must respect con...
Edward Gil Jones, M. Bernardine Dias, Anthony Sten...