Collaborative Online Learning of an Action Model

A number of recent works have designed algorithms that allow an agent to revise a relational action model from interactions with its environment and uses this model for building plans and better exploring its environment. This article addresses Multi Agent Relational Action Learning: it considers a community of agents, each rationally acting following some relational action model, and assumes that the observed effect of past actions that led an agent to revise its action model can be communicated to other agents of the community, potentially speeding up the on-line learning process of agents in the community. We describe and experiment a framework for collaborative relational action model revision where each agent is autonomous and benefits from past observations memorized by all agents of the community.

[1]  Mark Steedman,et al.  Learning STRIPS Operators from Noisy and Incomplete Observations , 2012, UAI.

[2]  Volker Klingspor,et al.  Learning concepts from sensor data of a mobile robot , 1996, Machine Learning.

[3]  Céline Rouveirol,et al.  Active Learning of Relational Action Models , 2011, ILP.

[4]  Richard S. Sutton,et al.  Dyna, an integrated architecture for learning, planning, and reacting , 1990, SGAR.

[5]  Amal El Fallah Seghrouchni,et al.  SMILE: Sound Multi-agent Incremental LEarning , 2007, AAMAS '07.

[6]  Qiang Yang,et al.  Learning action models from plan examples using weighted MAX-SAT , 2007, Artif. Intell..

[7]  Céline Rouveirol,et al.  A consistency based approach of action model learning in a community of agents , 2014, AAMAS.

[8]  Hendrik Blockeel,et al.  Top-Down Induction of First Order Logical Decision Trees , 1998, AI Commun..

[9]  John E. Laird,et al.  Instance-Based Online Learning of Deterministic Relational Action Models , 2010, AAAI.

[10]  Subbarao Kambhampati,et al.  Refining Incomplete Planning Domain Models Through Plan Traces , 2013, IJCAI.

[11]  Céline Rouveirol,et al.  Multi Agent Learning of Relational Action Models , 2014, ECAI.

[12]  Drew McDermott,et al.  The 1998 AI Planning Systems Competition , 2000, AI Mag..

[13]  Manuel Lopes,et al.  Active Learning for Teaching a Robot Grounded Relational Symbols , 2013, IJCAI.

[14]  L. P. Kaelbling,et al.  Learning Symbolic Models of Stochastic Domains , 2007, J. Artif. Intell. Res..

[15]  Luc De Raedt,et al.  Relational Reinforcement Learning , 2001, Machine Learning.

[16]  Marc Toussaint,et al.  Exploration in relational domains for model-based reinforcement learning , 2012, J. Mach. Learn. Res..

[17]  Jörg Hoffmann,et al.  FF: The Fast-Forward Planning System , 2001, AI Mag..

[18]  Céline Rouveirol,et al.  Incremental Learning of Relational Action Rules , 2010, 2010 Ninth International Conference on Machine Learning and Applications.

[19]  Amal El Fallah Seghrouchni,et al.  Collaborative Concept Learning: Non Individualistic vs Individualistic Agents , 2009, 2009 21st IEEE International Conference on Tools with Artificial Intelligence.

[20]  Ramón P. Otero,et al.  Induction of the Indirect Effects of Actions by Monotonic Methods , 2005, ILP.

[21]  Maurice Bruynooghe,et al.  Online Learning and Exploiting Relational Models in Reinforcement Learning , 2007, IJCAI.

[22]  Nicola Fanizzi,et al.  Incremental learning and concept drift in INTHELEX , 2004, Intell. Data Anal..

[23]  Katharina Morik,et al.  Sloppy Modeling , 1987, Knowledge Representation and Organization in Machine Learning.