Titlebook: Case-Based Reasoning Research and Development; 20th International C Belén Díaz Agudo,Ian Watson Conference proceedings 2012 Springer-Verlag

母豬

永久

Learning and Reusing Goal-Specific Policies for Goal-Driven Autonomy,t, and (3) actions for achieving these goals in given states. Our hypothesis is that, unlike RL, GRL can rapidly fine-tune strategies by exploiting the episodic knowledge captured in its cases. We report performance gains versus a state-of-the-art GDA agent and an RL agent for challenging tasks in two real-time video game domains.

涂掉

Conference proceedings 2012velopment (ICCBR 2012) held in Lyon, France, September 3-6, 2012. The 34 revised full papers presented were carefully selected from 51 submissions. The presentations and posters covered a wide range of CBR topics of interest to both practitioners and researchers, including foundational issues coveri

有法律效應(yīng)

0302-9743 roceedings of the 20th International Conference on Case-Based Reasoning Research and Development (ICCBR 2012) held in Lyon, France, September 3-6, 2012. The 34 revised full papers presented were carefully selected from 51 submissions. The presentations and posters covered a wide range of CBR topics

Explicate

箴言

sebaceous-gland

Promotion

Graphical Output and Visualization,d using it to contrast two such systems, identifying their relative strengths and weaknesses. To corroborate our analysis, we perform a comparative experimental evaluation of these systems on a real-time strategy game domain.

flaunt

Néstor G. Martínez,Alejandro Petrovichageous performance of vector similarity measures. This method is based on the assumption that events closer to a point of interest, like the current time, are more important than those further away. Four experiments are performed on both synthetic and real-time data that show both disadvantages and advantages of the method.

挑剔為人