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...
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. They help ov...
Research has shown promise in the design of large scale common sense probabilistic models to infer human state from environmental sensor data. These models have made use of mined ...
William Pentney, Matthai Philipose, Jeff A. Bilmes
Real world multiagent coordination problems are important issues for reinforcement learning techniques. In general, these problems are partially observable and this characteristic ...
Coarse-to-fine approaches use sequences of increasingly fine approximations to control the complexity of inference and learning. These techniques are often used in NLP and visio...