We present a new approximation method called value extrapolation for Markov processes with large or infinite state spaces. The method can be applied for calculating any performan...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
This paper presents a self-organizing cognitive architecture, known as TD-FALCON, that learns to function through its interaction with the environment. TD-FALCON learns the value ...
We present a novel Bayesian approach to the problem of value function estimation in continuous state spaces. We define a probabilistic generative model for the value function by i...
Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of ...