Adaptive Goal Driven Autonomy

The Rational Selection of Goal Operations and the Integration ofSearch Strategies with Goal-Driven Autonomy

“…Goal driven autonomy or GDA (Aha et al, 2010;Klenk et al, 2013;Munoz-Avila, 2018) is a kind of goal reasoning (Aha, 2018;Roberts et al, 2018) applied to issues of robust autonomy in agent-based systems. Unlike standard autonomous systems that generate behaviors given externally provided goals or tasks, the GDA approach is to independently recognize problems that arise, explain what causes the problem, and use the explanation to formulate a goal.…”

A Layered Architecture for Active Perception: Image Classification using Deep Reinforcement Learning

“…, while it has been detached from the gradients. This means that a machine learning algorithm should treat r (k) d as a non-differentiable scalar during training 2 Then, we inspect that…”

“…Different rollouts are required when the outcome of the game is uncertain (i.e., stochastic) [24]. 2 The reason for this treatment is because of the idea behind the chain rule: in (f g) = f g + g f , f and g in the right hand side correspond to being kept constant while the other term varies. Remark 1: The first term inside the summation in ( 14) is identical to the quantity that is derived in the policy gradient method with a reward which is independent of the parameters, i.e., the REINFORCE algorithm [7].…”

“…There has been a rapidly growing interest in goal reasoning in recent years; planning mechanisms for agents that are capable of explicitly reasoning about their goals and changing them whenever it becomes necessary [1], [2]. The potential applications of goal reasoning spans over several research fields, for example, only to name a few, controlling underwater unmanned vehicles [3], playing digital games [4], and air combat simulations [5].…”