Training robot or agent behaviors by example is an attractive alternative to directly coding them. However training complex behaviors can be challenging, particularly when it involves interactive behaviors involving multiple agents. We present a novel hierarchical learning from demonstration system which can be used to train both single-agent and scalable cooperative multiagent behaviors. The m...

At RoboCup, teams of autonomous robots or software softbots compete in simulated soccer matches to demonstrate cooperative robotics techniques in a very difficult, real-time, noisy environment. At the IJCAI/RoboCup97 softbot competition, all entries but ours used human-crafted cooperative decision-making behaviors. We instead entered a softbot team whose high-level decision making behaviors had...

In addition to researchers in AI and robotics, RoboCup attracts ordinary people, especially kids, high school and university students. Over 3000 people from 35 nations around the world have participated in RoboCup since the great success of the First Robot World Cup Soccer Games and Conferences, RoboCup-97 [1] held in conjunction with the Fifteenth International Joint Conference on Artificial I...

We present an approach to map Robocup-soccer narratives (in natural language) to a sequence of meaningful events. Our approach takes advantage of an action-centered framework, an inference subroutine, and an iterative learning algorithm. Our framework represents the narrative as a sequence of sentences and each sentence as a probability distribution over deterministic events. Our learning algor...

This paper presents the design and learning architecture for a fully holonomic omnidirectional walk used by the UT Austin Villa humanoid robot soccer agent acting in the RoboCup 3D simulation environment. By “fully holonomic” we mean the walk allows for movement in all directions with equal velocity. The walk is based on a double linear inverted pendulum model and was originally designed for th...

In this paper we will describe our research in case of using Expert System as a decision-making system. We made our attempt to expose a base strategy from past log files and implement an online learning system which receives information from the environment. In developing the coach, the main research effort comprises two complementary parts: (a) Design a rule-based expert system in which its ta...

The paper describes the architecture and the scientific goals of the virtual soccer team “AT Humboldt 99”, which is the successor of vice champion “AT Humboldt 98” from RoboCup-98 in Paris and world champion “AT Humboldt 97” from RoboCup-97 in Nagoya. Scientific goals are the development of agent-oriented techniques and learning methods.

Our last years Soccer Simulation team AT Humboldt 2003 was mainly designed as a research testbed for long-term deliberation and realtime reasoning, cooperative behavior in MAS, CBR-aided decision making and scalable behavior control mechanisms. The main goal was to implement and to evaluate the double pass architecture (DPA). This was always done with regard to the transition of the Simulation ...

The paper describes the architecture and the scientiic goals of the virtual soccer team \AT Humboldt 99", which is the successor of vice champion \AT Humboldt 98" from RoboCup-98 in Paris and world champion \AT Humboldt 97" from RoboCup-97 in Nagoya. Scientiic goals are the development of agent-oriented techniques and learning methods.