This paper presents a general and efficient framework for probabilistic inference and learning from arbitrary uncertain information. It exploits the calculation properties of finite mixture models, conjugate families and factorization. Both the joint probability density of the variables and the likelihood function of the (objective or subjective) observation are approximated by a special mixture model, in such a way that any desired conditional distribution can be directly obtained without numerical integration. We have developed an extended version of the expectation maximization (EM) algorithm to estimate the parameters of mixture models from uncertain training examples (indirect observations). As a consequence, any piece of exact or uncertain information about both input and output values is consistently handled in the inference and learning stages. This ability, extremely useful in certain situations, is not found in most alternative methods. The proposed framework is formally justified from standard probabilistic principles and illustrative examples are provided in the fields of nonparametric pattern classification, nonlinear regression and pattern completion. Finally, experiments on a real application and comparative results over standard databases provide empirical evidence of the utility of the method in a wide range of applications.

Robotic soccer is a challenging research domain that involves multiple agents that need to collaborate in an adversarial environment to achieve specific objectives. In this article, we describe CMUNITED, the team of small robotic agents that we developed to enter the RoboCup-97 competition. We designed and built the robotic agents, devised the appropriate vision algorithm, and developed and implemented algorithms for strategic collaboration between the robots in an uncertain and dynamic environment. The robots can organize themselves in formations, hold specific roles, and pursue their goals. In game situations, they have demonstrated their collaborative behaviors on multiple occasions. We present an overview of the vision-processing algorithm that successfully tracks multiple moving objects and predicts trajectories. The article then focuses on the agent behaviors, ranging from low-level individual behaviors to coordinated, strategic team behaviors. CMUNITED won the RoboCup-97 small-robot competition at the Fifteenth International Joint Conference on Artificial Intelligence in Nagoya, Japan.

Robot soccer competition provides an excellent opportunity for integrated robotics research. In particular, robot players in a soccer game must recognize and track objects in real time, navigate in a dynamic field, collaborate with teammates, and strike the ball in the correct direction. All these tasks demand robots that are autonomous (sensing, thinking, and acting as independent creatures), efficient (functioning under time and resource constraints), cooperative (collaborating with each other to accomplish tasks that are beyond an individual's capabilities), and intelligent (reasoning and planning actions and perhaps learning from experience). Furthermore, all these capabilities must be integrated into a single and complete system, which raises a set of challenges that are new to individual research disciplines. This article describes our experience (problems and solutions) in these aspects. Our robots share the same general architecture and basic hardware, but they have integrated abilities to play different roles (goalkeeper, defender, or forward) and use different strategies in their behavior. Our philosophy in building these robots is to use the least sophistication to make them as robust and integrated as possible. At RoboCup-97, held as part of the Fifteenth International Joint Conference on Artificial Intelligence, these integrated robots performed well, and our DREAMTEAM won the world championship in the middle-size robot league.

RoboCup-97, The First Robot World Cup Soccer Games and Conferences, was held at the Fifteenth International Joint Conference on Artificial Intelligence. There were two leagues: (1) real robot and (2) simulation. Ten teams participated in the real-robot league and 29 teams in the simulation league. Over 150 researchers attended the technical workshop. The world champions are CMUNITED (Carnegie Mellon University) for the small-size league, DREAMTEAM (University of Southern California) and TRACKIES (Osaka University, Japan) for the middle-size league, and AT-HUMBOLDT (Humboldt University) for the simulation league. The Scientific Challenge Award was given to Sean Luke (University of Maryland) for his genetic programming- based simulation team LUKE, and the Engineering Challenge Awards were given to UTTORI UNITED (Utsunomiya University, Toyo University, and Riken, Japan) and RMIT (Royal Melbourne Institute of Technology, Australia) for designing novel omnidirectional driving mechanisms. Over 5000 spectators and 70 international media covered the competition worldwide. RoboCup-98, the Second Robot World Cup Soccer, was held in conjunction with the Third International Conference on Multiagent Systems in Paris, France, in July 1998.

's performance in is driven by's development was driven by the Using Further aspects of multiagent agents could not always quickly locate and agent and team modeling. With respect to learning, as well as arenas of agent and intercept the ball or maintain awareness of teamwork, our previous work was based on team modeling (particularly to recognize positions of teammates and opponents. It then enables team members to make any decisions. Instead, all the decision Yaser Al-Onaizan, Ali Erdem, autonomously reason about coordination making rests with the higher level, Gal A. Kaminka, Stacy C. Marsella, and communication in teamwork, providing implemented in the Given its domain architecture, which takes into account the independence, it also enables reuse across recommendations made by the lower level. 's teamwork reasoning is currently test domain given its substantial also implemented in

In this article, we describe the milestone of our research efforts in our work for the RoboCup middle-size league competition. Reinforcement learning in applying it to real robot applications; we then give our method of coping with these has recently been receiving increased attention issues in the context of RoboCup. Finally, we as a method for robot learning with little or no show our system and the experimental results a priori knowledge and a higher capability for of RoboCup-97. The robot senses the current state First, we follow the explanation of Q-learning of the environment and selects an action. For a more thorough treatment, Based on the state and the action, the environment see Watkins and Dayan (1992).

We applied mobile computing to community support and explored mobile computing with a large number of terminals. This article reports on the Second International Conference on Multiagent Systems (ICMAS'96) Mobile Assistant Project that was conducted at an actual international conference for multiagent systems using 100 personal digital assistants (PDAs) and cellular telephones. We supported three types of service: (1) communication services such as e-mail and net news; (2) information services such as conference, personal, and tourist information; and (3) community support services such as forum and meeting arrangements. After the conference, we analyzed a large amount of log data and obtained the following results: It appears that people continuously used PDAs in their hotel rooms after dinner; e-mail services were used independently of the conference structure, but the load on information services reflected the schedule of the conference. Postquestionnaire data showed that our trial was considered interesting, although people were not fully satisfied with the PDAs and services provided. Participants showed a deep interest in mobile computing for community support.

One of the most common mechanisms used for speeding up problem solvers is macro-learning. Macros are sequences of basic operators acquired during problem solving. Macros are used by the problem solver as if they were basic operators. The major problem that macro-learning presents is the vast number of macros that are available for acquisition. Macros increase the branching factor of the search space and can severely degrade problem-solving efficiency. To make macro learning useful, a program must be selective in acquiring and utilizing macros. This paper describes a general method for selective acquisition of macros. Solvable training problems are generated in increasing order of difficulty. The only macros acquired are those that take the problem solver out of a local minimum to a better state. The utility of the method is demonstrated in several domains, including the domain of NxN sliding-tile puzzles. After learning on small puzzles, the system is able to efficiently solve puzzles of any size.

In this paper we consider the problem of `theory patching', in which we are given a domain theory, some of whose components are indicated to be possibly flawed, and a set of labeled training examples for the domain concept. The theory patching problem is to revise only the indicated components of the theory, such that the resulting theory correctly classifies all the training examples. Theory patching is thus a type of theory revision in which revisions are made to individual components of the theory. Our concern in this paper is to determine for which classes of logical domain theories the theory patching problem is tractable. We consider both propositional and first-order domain theories, and show that the theory patching problem is equivalent to that of determining what information contained in a theory is `stable' regardless of what revisions might be performed to the theory. We show that determining stability is tractable if the input theory satisfies two conditions: that revisions to each theory component have monotonic effects on the classification of examples, and that theory components act independently in the classification of examples in the theory. We also show how the concepts introduced can be used to determine the soundness and completeness of particular theory patching algorithms.

By now it is widely accepted that learning a task from scratch, i.e., without any prior knowledge, is a daunting undertaking. Humans, however, rarely attempt to learn from scratch. They extract initial biases as well as strategies how to approach a learning problem from instructions and/or demonstrations of other humans. For learning control, this paper investigates how learning from demonstration can be applied in the context of reinforcement learning. We consider priming the Q-function, the value function, the policy, and the model of the task dynamics as possible areas where demonstrations can speed up learning. In general nonlinear learning problems, only model-based reinforcement learning shows significant speedup after a demonstration, while in the special case of linear quadratic regulator (LQR) problems, all methods profit from the demonstration. In an implementation of pole balancing on a complex anthropomorphic robot arm, we demonstrate that, when facing the complexities of real signal processing, model-based reinforcement learning offers the most robustness for LQR problems. Using the suggested methods, the robot learns pole balancing in just a single trial after a 30 second long demonstration of the human instructor.