Modular Design Patterns for Hybrid Actors

09/20/2021

∙

Recently, a boxology (graphical language) with design patterns for hybrid AI was proposed, combining symbolic and sub-symbolic learning and reasoning. In this paper, we extend this boxology with actors and their interactions. The main contributions of this paper are: 1) an extension of the taxonomy to describe distributed hybrid AI systems with actors and interactions; and 2) showing examples using a few design patterns relevant in multi-agent systems and human-agent interaction.

READ FULL TEXT

Modular Design Patterns for Hybrid Actors

Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases

Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

Modular design patterns for neural-symbolic integration: refinement and combination

Embracing AWKWARD! Real-time Adjustment of Reactive Plans Using Social Norms

Applying Autonomous Hybrid Agent-based Computing to Difficult Optimization Problems

R-CHECK: A Model Checker for Verifying Reconfigurable MAS

Effective Integration of Symbolic and Connectionist Approaches through a Hybrid Representation

Modular Design Patterns for Hybrid Actors

Related Research

Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases

Beyond Traditional Neural Networks: Toward adding Reasoning and Learning Capabilities through Computational Logic Techniques

Modular design patterns for neural-symbolic integration: refinement and combination

Embracing AWKWARD! Real-time Adjustment of Reactive Plans Using Social Norms

Applying Autonomous Hybrid Agent-based Computing to Difficult Optimization Problems

R-CHECK: A Model Checker for Verifying Reconfigurable MAS

Effective Integration of Symbolic and Connectionist Approaches through a Hybrid Representation