A characterization of sapient agents

We present a proposal to characterize sapient agents in terms of cognitive concepts and abilities. In particular, a sapient agent is considered as a cognitive agent that learns its cognitive state and capabilities through experience. This characterization is based on formal concepts such as beliefs, goals, plans and reasoning rules, and formal techniques such as relational RL. We identify several aspects of cognitive agents that can be evolved through learning and indicate how these aspects can be learned. Other important features such as the social environment, interaction with other agents or humans and the ability to deal with emotions, will also be discussed. Finally, the directions for further research on sapient agents are described.

[1]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[2]  C. Watkins.  Learning from delayed rewards , 1989 .

[3]  Anand S. Rao,et al.  Modeling Rational Agents within a BDI-Architecture , 1997, KR.

[4]  G. Tesauro.  Practical Issues in Temporal Difference Learning , 1992 .

[5]  Michael L. Littman,et al.  A Distributed Reinforcement Learning Scheme for Network Routing , 1993 .

[6]  A. Damasio.  Descartes’ Error. Emotion, Reason and the Human Brain. New York (Grosset/Putnam) 1994. , 1994 .

[7]  A. Damasio.  Descartes' error: emotion, reason, and the human brain. avon books , 1994 .

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

[9]  Andrew G. Barto,et al.  Improving Elevator Performance Using Reinforcement Learning , 1995, NIPS.

[10]  A. S. Roa,et al.  AgentSpeak(L): BDI agents speak out in a logical computable language , 1996 .

[11]  Michael Wooldridge,et al.  A Formal Specification of dMARS , 1997, ATAL.

[12]  Rosalind W. Picard.  Affective Computing , 1997 .

[13]  Stuart J. Russell,et al.  Reinforcement Learning with Hierarchies of Machines , 1997, NIPS.

[14]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[15]  Gerhard Weiss,et al.  Multiagent systems: a modern approach to distributed artificial intelligence , 1999 .

[16]  Marco Wiering,et al.  Multi-Agent Reinforcement Learning for Traffic Light control , 2000 .

[17]  Thomas G. Dietterich.  Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition , 1999, J. Artif. Intell. Res..

[18]  Leonid Sheremetov,et al.  Weiss, Gerhard. Multiagent Systems a Modern Approach to Distributed Artificial Intelligence , 2009 .

[19]  Raymond Reiter,et al.  Knowledge in Action: Logical Foundations for Specifying and Implementing Dynamical Systems , 2001 .

[20]  Craig Boutilier,et al.  Symbolic Dynamic Programming for First-Order MDPs , 2001, IJCAI.

[21]  Saso Dzeroski.  Relational Reinforcement Learning for Agents in Worlds with Objects , 2002, Adaptive Agents and Multi-Agents Systems.

[22]  Alex M. Andrew,et al.  Knowledge in Action: Logical Foundations for Specifying and Implementing Dynamical Systems , 2002 .

[23]  van Martijn Otterlo.  Relational Representations in Reinforcement Learning: Review and Open Problems , 2002, ICML 2002.

[24]  Mehdi Dastani,et al.  Goal generation in the BOID architecture , 2002 .

[25]  Frank Dignum,et al.  Autonomy and Agent Deliberation , 2003, Agents and Computational Autonomy.

[26]  Frank Dignum,et al.  Programming agent deliberation: an approach illustrated using the 3APL language , 2003, AAMAS '03.

[27]  M. van Otterlo.  Efficient Reinforcement Learning using Relational Aggregation , 2003 .

[28]  Frank Dignum,et al.  A Programming Language for Cognitive Agents Goal Directed 3APL , 2003, PROMAS.

[29]  Koen V. Hindriks,et al.  Agent Programming in 3APL , 1999, Autonomous Agents and Multi-Agent Systems.

[30]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.