This paper studies a novel paradigm for learning formal languages from positive and negative examples which consists of mapping strings to an appropriate highdimensional feature s...
The development of the XCS Learning Classifier System [26] has produced a stable implementation, able to consistently identify the accurate and optimally general population of cla...
Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithmshave appeared that approximatedynamic programming on an ...
Many real-world domains exhibit rich relational structure and stochasticity and motivate the development of models that combine predicate logic with probabilities. These models de...
Sriraam Natarajan, Prasad Tadepalli, Eric Altendor...
One of the central challenges in reinforcement learning is to balance the exploration/exploitation tradeoff while scaling up to large problems. Although model-based reinforcement ...