Modeling synthetic characters which interact with objects in dynamic virtual worlds is important when we want the agents to act in an autonomous and non-preplanned way. Such inter...
Recent advancements in model-based reinforcement learning have shown that the dynamics of many structured domains (e.g. DBNs) can be learned with tractable sample complexity, desp...
Thomas J. Walsh, Sergiu Goschin, Michael L. Littma...
Monaural speech segregation in reverberant environments is a very difficult problem. We develop a supervised learning approach by proposing an objective function that directly rel...
Godin, R. and R. Missaoui, An incremental concept formation approach for learning from databases, Theoretical Computer Science 133 (1994) 3533385. This paper describes a concept f...
This paper introduces a partition of the possible forms of knowledge according to their rela tionship to the basic objective of an intelligent agent, namely to act successfully ...