91 search results - page 17 / 19 » Parameter-exploring policy gradients |
ICONIP
2007
13 years 9 months ago
2007
The aim of the Cyber Rodent project [1] is to elucidate the origin of our reward and affective systems by building artificial agents that share the natural biological constraints...
EDBT
2008
ACM
14 years 7 months ago
2008
ACM
Modern enterprise data warehouses have complex workloads that are notoriously difficult to manage. An important problem in workload management is to run these complex workloads `o...
ATAL
2007
Springer
14 years 1 months ago
2007
Springer
Classically, an approach to the multiagent policy learning supposed that the agents, via interactions and/or by using preliminary knowledge about the reward functions of all playe...
JMLR
2010
13 years 2 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
DAC
2009
ACM
14 years 2 months ago
2009
ACM
It is known that temperature gradients and thermal hotspots affect the reliability of microprocessors. Temperature is also an important constraint when maximizing the performance...