Research Repository

Planning using online evolutionary overfitting

Samothrakis, S and Lucas, SM (2010) Planning using online evolutionary overfitting. In: UNSPECIFIED, ? - ?.

Full text not available from this repository.


Biological systems tend to perform a range of tasks of extreme variability with extraordinary efficiency. It has been argued that a plausible scenario for achieving such versatility is explicitly learning a forward model. We perform a set of experiments using the original and a modified version of a classic reinforcement learning task, the mountain car problem, using a number of agents that encode both a direct and an abstracted version of a forward model. The results suggest that superior performance can be achieved if the forward model can be exploited in real-time by an agent that has already internalised a model-free control function.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: 2010 UK Workshop on Computational Intelligence, UKCI 2010
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Jim Jamieson
Date Deposited: 19 Oct 2012 14:36
Last Modified: 23 Jan 2019 02:15

Actions (login required)

View Item View Item