Case-Based Planning (CBP) provides a way of scaling up domain-independent planning to solve large problems in complex domains. It replaces the detailed and lengthy search for a solution with the retrieval and adaptation of previous planning experiences. In general, CBP has been demonstrated to improve performance over generative (from-scratch) planning. However, the performance improvements it provides are dependent on adequate judgements as to problem similarity. In particular, although CBP may substantially reduce planning e ort overall, it is subject to a mis-retrieval problem. The success of CBP depends on these retrieval errors being relatively rare. This paper describes the design and implementation of a replay framework for the case-based planner dersnlp+ebl. der-snlp+ebl extends current CBP methodology by incorporating explanation-based learning techniques that allow it to explain and learn from the retrieval failures it encounters. These techniques are used to re ne judgements about case similarity in response to feedback when a wrong decision has been made. The same failure analysis is used in building the case library, through the addition of repairing cases. Large problems are split and stored as single goal subproblems. Multi-goal problems are stored only when these smaller cases fail to be merged into a full solution. An empirical evaluation of this approach demonstrates the advantage of learning from experienced retrieval failure.

The current study demonstrates a new class of objective information, namely, that young infants can use their mother's position as a spatial landmark. Ninemonth-old infants learned to turn one way to view a visual event. In a transfer task, they were rotated 180°. The mothers of half of the infants moved with them, as in previous procedures. The mothers of the other infants remained in a fixed position throughout training and testing. The infants made more turns to the same spatial location when their mothers did not move. Thus, young infants used their mother's position as a cue to their spatial response. Although their mother's position is not always a reliable spatial cue and its use can often lead to "errors," it is a cue that is certainly not egocentric. The use of mother as a spatial landmark in the current study suggests that even in situations in which young infants have been judged egocentric, they may be using objective, nonegocentric information. Thus, it is important to recognize that even apparent errors do not preclude the presence of objective representation.

No abstract

No abstract

No abstract