A self-organizing neural network architecture for intentional planning agents

This paper presents a model of neural network embodiment of intentions and planning mechanisms for autonomous agents. The model bridges the dichotomy of symbolic and non-symbolic representation in developing agents. Some novel techniques are introduced that enables the neural network to process and manipulate sequential and hierarchical structures of information. It is suggested that by incorporating intentional agent model which relies on explicit symbolic description with self-organizing neural networks that are good at learning and recognizing patterns, the best from both sides can be exploited. This paper demonstrates that plans can be represented as weighted connections and reasoning processes can be accommodated through multi-directional activations accross different modalities of patterns. The network seamlessly interleaves planning and learning processes towards achieving the goal. Case studies and experiments shows that the model can be used to execute, plan, and capture plans as recipes through experiences.

[1]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[2]  H. Simon,et al.  Models of Bounded Rationality: Empirically Grounded Economic Reason , 1997 .

[3]  Paolo Traverso,et al.  Automated planning - theory and practice , 2004 .

[4]  Ah-Hwee Tan,et al.  FALCON: a fusion architecture for learning, cognition, and navigation , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[5]  Anand S. Rao,et al.  BDI Agents: From Theory to Practice , 1995, ICMAS.

[6]  S. Grossberg.  Behavioral Contrast in Short Term Memory: Serial Binary Memory Models or Parallel Continuous Memory Models? , 1978 .

[7]  Stephen Grossberg,et al.  Intelligence Through Interaction: Towards a Unified Theory for Learning , 2007, ISNN.

[8]  Martha E. Pollack,et al.  The Uses of Plans , 1992, Artif. Intell..

[9]  Ah-Hwee Tan,et al.  Integrating Temporal Difference Methods and Self-Organizing Neural Networks for Reinforcement Learning With Delayed Evaluative Feedback , 2008, IEEE Transactions on Neural Networks.

[10]  Michael P. Georgeff,et al.  Commitment and Effectiveness of Situated Agents , 1991, IJCAI.

[11]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[12]  Stephex GROSSBERGl.  Behavioral Contrast in Short Term Memory : Serial Binary Memory Models or Parallel Continuous Memory Models ? , 2003 .

[13]  Paolo Traverso,et al.  Automated Planning: Theory & Practice , 2004 .

[14]  Stephen Grossberg,et al.  Adaptive Resonance Theory , 2010, Encyclopedia of Machine Learning.

[15]  Philip R. Cohen,et al.  Plans as Complex Mental Attitudes , 2003 .

[16]  D. Dennett.  The Intentional Stance. , 1987 .

[17]  Anand S. Rao,et al.  An architecture for real-time reasoning and system control , 1992, IEEE Expert.

[18]  S. Brison.  The Intentional Stance , 1989 .

[19]  Michael E. Bratman,et al.  What is intention , 1987 .

[20]  Michael Wooldridge,et al.  The theory and practice of intention reconsideration , 2004, J. Exp. Theor. Artif. Intell..

[21]  Stephen Grossberg,et al.  STORE working memory networks for storage and recall of arbitrary temporal sequences , 1994, Biological Cybernetics.

[22]  Steven M. LaValle,et al.  Planning algorithms , 2006 .