A Novel Model for Arbitration between Planning and Habitual Control Systems

by   Farzaneh S. Fard, et al.

It is well established that humans decision making and instrumental control uses multiple systems, some which use habitual action selection and some which require deliberate planning. Deliberate planning systems use predictions of action-outcomes using an internal model of the agent's environment, while habitual action selection systems learn to automate by repeating previously rewarded actions. Habitual control is computationally efficient but may be inflexible in changing environments. Conversely, deliberate planning may be computationally expensive, but flexible in dynamic environments. This paper proposes a general architecture comprising both control paradigms by introducing an arbitrator that controls which subsystem is used at any time. This system is implemented for a target-reaching task with a simulated two-joint robotic arm that comprises a supervised internal model and deep reinforcement learning. Through permutation of target-reaching conditions, we demonstrate that the proposed is capable of rapidly learning kinematics of the system without a priori knowledge, and is robust to (A) changing environmental reward and kinematics, and (B) occluded vision. The arbitrator model is compared to exclusive deliberate planning with the internal model and exclusive habitual control instances of the model. The results show how such a model can harness the benefits of both systems, using fast decisions in reliable circumstances while optimizing performance in changing environments. In addition, the proposed model learns very fast. Finally, the system which includes internal models is able to reach the target under the visual occlusion, while the pure habitual system is unable to operate sufficiently under such conditions.


Continuous Control for Searching and Planning with a Learned Model

Decision-making agents with planning capabilities have achieved huge suc...

A Model for Combination of External and Internal Stimuli in the Action Selection of an Autonomous Agent

This paper proposes a model for combination of external and internal sti...

A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control

Reinforcement Learning (RL) is a method for learning decision-making tas...

Action Selection Properties in a Software Simulated Agent

This article analyses the properties of the Internal Behaviour network, ...

Pathfinding in Random Partially Observable Environments with Vision-Informed Deep Reinforcement Learning

Deep reinforcement learning is a technique for solving problems in a var...

A constrained control-planning strategy for redundant manipulators

This paper presents an interconnected control-planning strategy for redu...

Long-Term Planning and Situational Awareness in OpenAI Five

Understanding how knowledge about the world is represented within model-...

Please sign up or login with your details

Forgot password? Click here to reset