Evolving Teleo-Reactive Programs for Block Stacking using Indexicals through Genetic Programming
نویسنده
چکیده
This paper demonstrates how strongly-typed genetic programming may be used to evolve valid teleo-reactive programs that solve the general block-stacking problem using indexicals.
منابع مشابه
Evolving Hierarchical and Recursive Teleo-reactive Programs through Genetic Programming
Teleo-reactive programs and the triple tower architecture have been proposed as a framework for linking perception and action in agents. The triple tower architecture continually updates the agent’s knowledge of the world and evokes actions according to teleo-reactive control structures. This paper uses block stacking problems to demonstrate how genetic programming may be used to evolve hierarc...
متن کاملNeural Synthesis of Teleo-reactive Programs Teleo-reactive Programs
The Teleo-Reactive (TR) formalism has been presented as a new programming paradigm to write agent programs with reactive control and goal oriented behavior. The formalism is based in a circuit semantics that intuitively can be ported directly to a layered AND/OR neural network architecture. But to capture the essence of the TR paradigm, a more sophisticated mechanism of synthesis must be develo...
متن کاملGRUE: A Goal Processing Architecture for Game Agents
Computer games are becoming increasingly popular as a research platform for agents research and applications. A key problem for game agents is responding in a timely and appropriate way to multiple, often conflicting goals in a complex, dynamic environment. In this paper we propose a novel goal processing architecture for game agents. Building on the teleo-reactive programming framework origina...
متن کاملA Hybrid, Teleo-Reactive Architecture for Robot Control
In this paper we describe the structure of a proposed hybrid architecture for robot control. A BDI-style planning layer manipulates a plan library in which plans are comprised of hierarchical, suspendable and recoverable teleo-reactive programs. We also present preliminary simulation and implementation work.
متن کاملImplementing a teleo-reactive programming system
Acknowledgements I would like to express my gratitude to Dr Anthony Field for his support and guidance throughout my project. I would also like to thank Dr Keith Clark and Dr Peter Robinson for their support with the Qulog software and discussion in person and via email. Finally, I thank my family, my friends and all my professors at Imperial College. 2 This thesis explores the teleo-reactive p...
متن کامل