We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
We propose a novel Bayesian learning framework of hierarchical mixture model by incorporating prior hierarchical knowledge into concept representations of multi-level concept struc...
Evolutionary algorithms tend to produce solutions that are not evolvable: Although current fitness may be high, further search is impeded as the effects of mutation and crossover ...
Abstract-- We propose a method of correlating circuit performance with technology fluctuations during the circuit-design phase. The method employs test circuits sensitive for techn...
Usage-based pricing of offered traffic to a data network can be an effective technique for congestion control. To gain insight into the benejits usage-based pricing offers, we pro...