28 search results - page 4 / 6 » Transferring knowledge as heuristics in reinforcement learni... |
ILP
2007
Springer
14 years 2 months ago
2007
Springer
We describe an application of inductive logic programming to transfer learning. Transfer learning is the use of knowledge learned in a source task to improve learning in a related ...
AGI
2008
13 years 10 months ago
2008
In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had ma...
CORR
2012
Springer
12 years 4 months ago
2012
Springer
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, lar...
ICMLA
2009
13 years 6 months ago
2009
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
AAAI
2010
13 years 9 months ago
2010
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...