Shaping robot behavior using principles from instrumental conditioning

نویسندگان

  • Lisa M. Saksida
  • Scott M. Raymond
  • David S. Touretzky
چکیده

Shaping by successive approximations is an important animal training technique in which behavior is gradually adjusted in response to strategically timed reinforcements. We describe a computational model of this shaping process and its implementation on a mobile robot. Innate behaviors in our model are sequences of actions and enabling conditions, and shaping is a behavior editing process realized by multiple editing mechanisms. The model replicates some fundamental phenomena associated with instrumental learning in animals, and allows an RWI B21 robot to learn several distinct tasks derived from the same innate behavior.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Control of Flexible Link Robot using a Closed Loop Input-Shaping Approach

This paper is has addressed the Single Flexible Link Robot. The dynamical model is derived using Euler-Lagrange equation and then a proper controller is designed to suppress a  vibration based-on Input-Shaping (IS) method. But, IS control method is an open loop strategy. Due to the weakness of open loop control systems, a closed loop IS control system is proposed. The achieved closed loop c...

متن کامل

Direct instrumental conditioning of neural activity using functional magnetic resonance imaging-derived reward feedback.

Successful learning is often contingent on feedback. In instrumental conditioning, an animal or human learns to perform specific responses to obtain reward. Instrumental conditioning is often used by behavioral psychologists to train an animal (or human) to produce a desired behavior. Shaping involves reinforcing those behaviors, which in a stepwise manner are successively closer to the desired...

متن کامل

Learning in and from brain-based devices.

Biologically based mobile devices have been constructed that differ from robots based on artificial intelligence. These brain-based devices (BBDs) contain simulated brains that autonomously categorize signals from the environment without a priori instruction. Two such BBDs, Darwin VII and Darwin X, are described here. Darwin VII recognizes objects and links categories to behavior through instru...

متن کامل

From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior (SAB96), pp. 285-

Instrumental (or operant) conditioning, a form of animal learning, is similar to reinforcement learning in that it allows an agent to adapt its actions to gain maximally from the environment while only being rewarded for correct performance. But animals learn much more complicated behaviors through instrumental conditioning than robots presently acquire through reinforcement learning. We descri...

متن کامل

Molecular substrates of action control in cortico-striatal circuits.

The purpose of this review is to describe the molecular mechanisms in the striatum that mediate reward-based learning and action control during instrumental conditioning. Experiments assessing the neural bases of instrumental conditioning have uncovered functional circuits in the striatum, including dorsal and ventral striatal sub-regions, involved in action-outcome learning, stimulus-response ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Robotics and Autonomous Systems

دوره 22  شماره 

صفحات  -

تاریخ انتشار 1997