Learning to Reason About Actions
نویسندگان
چکیده
We focus on learning representations of dynamical systems that can be characterized by logic-based formalisms for reasoning about actions and change, where system’s behaviors are naturally viewed as appropriate logical consequences of the domain’s description. To this end, logic-based induction methods are adapted to identify the input/output behavior of a dynamical system corresponding to an environment. The study of dynamic domains is started with domains modelable with classical action theories and is progressively enhanced to manage more complex behaviors.
منابع مشابه
A Q-learning Based Continuous Tuning of Fuzzy Wall Tracking
A simple easy to implement algorithm is proposed to address wall tracking task of an autonomous robot. The robot should navigate in unknown environments, find the nearest wall, and track it solely based on locally sensed data. The proposed method benefits from coupling fuzzy logic and Q-learning to meet requirements of autonomous navigations. Fuzzy if-then rules provide a reliable decision maki...
متن کاملWhat Can I Not Do? Towards an Architecture for Reasoning about and Learning Affordances
This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational r...
متن کاملThe Position of Implicit and Indirect Learning in Ethical Education
The rationalist approach has been dominated on the education environment of values for many years. Unilateral and excessive focus on this approach has revealed ignorance of a vast part of human implicit learning and his intuitive ethical judgments which have been the source of many ethical behaviors. The study intends to answer the question that why only direct and deductive educations about va...
متن کاملThe Concurrent, Continuous Fluent Calculus
The Fluent Calculus belongs to the established predicate calculus formalisms for reasoning about actions. Its underlying concept of state update axioms provides a solution to the basic representational and inferential Frame Problems in pure first-order logic. Extending a recent research result, we present a Fluent Calculus to reason about domains involving continuous change and where actions oc...
متن کاملMapping Instructions and Visual Observations to Actions with Reinforcement Learning
We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we learn a single model to jointly reason about linguistic and visual input. We use reinforcement learning in a contextual bandit setting to train a neural network...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000