Learning to problem solve requires acquiring multiple forms of knowledge. Problem solving is viewed as a search of a state-space formulation of a problem. With this formalism, operators are applied to states to transit from the intiial state to the goal state. The learning task is to acquire knowledge of that state-space to guide search. In particular, three forms of knowledge are required: why each operator is useful, when to apply each operator, and what each operator does. A PROLOG implementation, named PET, demonstrates the learning approach in the domains of simultaneous linear equations and symbolic integration.
Episodic learning is a technique for learning why individual operators are useful in a solution path. Episodic learning acquires generalized operator sequences which achieve the goal state. This is done by backing-up state evaluation and learning sub-goals in the state-space.
Perturbation is a technique for learning when individual operators are useful. Perturbation guides the generalization process to discover minimally-constained preconditions for useful operator applications. This is done by experimentation, thereby reducing the teacher's role in the learning process.
Learning relational models is a technique for discovering what individual operators do. Relational models are an explicit representation of the transformation performed by operators. This representation enables the learning element to reason with operator semantics to guide further learning.
Episodic learning, perturbation and relational models form an integrated approach for learning problem solving. The approach demonstrates self-teaching by reasoned experimentation.
