343 search results - page 56 / 69 » Action discovery for reinforcement learning |
ESANN
2007
13 years 9 months ago
2007
This paper presents our Recurrent Control Neural Network (RCNN), which is a model-based approach for a data-efficient modelling and control of reinforcement learning problems in di...
AAAI
2010
13 years 9 months ago
2010
The selection of the action to do next is one of the central problems faced by autonomous agents. In AI, three approaches have been used to address this problem: the programming-b...
NIPS
1992
13 years 8 months ago
1992
How can artificial neural nets generalize better from fewer examples? In order to generalize successfully, neural network learning methods typically require large training data se...
GLOBECOM
2008
IEEE
13 years 7 months ago
2008
IEEE
Traditional hop-by-hop dynamic routing makes inefficient use of network resources as it forwards packets along already congested shortest paths while uncongested longer paths may b...
ATAL
2004
Springer
14 years 1 months ago
2004
Springer
Single-agent reinforcement learners in time-extended domains and multi-agent systems share a common dilemma known as the credit assignment problem. Multi-agent systems have the st...