Learning through overcoming inheritance inconsistencies

In our previous work, we described a framework called i²Learning for a perpetual learning agent to be engaged in continuous learning to incrementally improve its problem solving performance over time. i²Learning offers an overarching framework that can accommodate various inconsistency-specific learning strategies. In this paper, we report our new results on how learning can be carried out through overcoming inheritance inconsistencies the agent encounters during its problem-solving episodes. Each learning episode causes the agent´s knowledge to be refined or augmented so as to overcome the encountered inheritance inconsistency. This will in turn improve the agent´s performance at tasks incrementally. The work in this paper is an integral part of the overall effort toward fully developing the i²Learning framework.