Goal-driven active learning

Goal-Driven Learning

Learning as Goal-Driven Inference

types of learning activities. These are instantiated with domain-specific information in the context of the performance task to yield domain-specific learning goals which, in turn, are used to drive learning. 4 Goal Dependency Networks In general, an intelligent system will have multiple learning goals that are interrelated in a very complex manner. In order to reason about the interactions bet...

Towards Goal-Driven Reflective Learning

Except for various ad hoc (and sometimes quite successful) systems, this de facto manifesto calling for the study of introspective systems did not give rise to what may be called "a general architecture for declarative and/or reflective machine learning". Some recent research taking place under the label of "goal-driven learning" signals however a renewed interest in these very basic issues: " ...

Learning and Reusing Goal-Specific Policies for Goal-Driven Autonomy

In certain adversarial environments, reinforcement learning (RL) techniques require a prohibitively large number of episodes to learn a highperforming strategy for action selection. For example, Q-learning is particularly slow to learn a policy to win complex strategy games. We propose GRL, the first GDA system capable of learning and reusing goal-specific policies. GRL is a case-based goal-dri...

Integrated Learning for Goal-Driven Autonomy

Goal-driven autonomy (GDA) is a reflective model of goal reasoning that controls the focus of an agent’s planning activities by dynamically resolving unexpected discrepancies in the world state, which frequently arise when solving tasks in complex environments. GDA agents have performed well on such tasks by integrating methods for discrepancy recognition, explanation, goal formulation, and goa...