123
click to vote
ECML
2006
Springer
15 years 6 months ago
2006
Springer
This paper studies the PAC and agnostic PAC learnability of some standard function classes in the learning in higher-order logic setting introduced by Lloyd et al. In particular, i...
111
click to vote
ECML
2006
Springer
15 years 6 months ago
2006
Springer
In this paper we formulate the problem of grouping the states of a discrete Markov chain of arbitrary order simultaneously with deconvolving its transition probabilities. As the na...
139
click to vote
ECML
2006
Springer
15 years 6 months ago
2006
Springer
Causal independence modelling is a well-known method both for reducing the size of probability tables and for explaining the underlying mechanisms in Bayesian networks. In this pap...
168
click to vote
ECML
2006
Springer
15 years 6 months ago
2006
Springer
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...
126
click to vote
ECML
2006
Springer
15 years 6 months ago
2006
Springer
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...