Reactive, Integrated Systems Pose New Problems for Machine Learning

Publisher Summary Most research on machine learning and planning has involved performance systems based on classical problem-solving algorithms (for example, STRIPS-Iike planners). AI problem solving has taken various divergent roads from these classical roots; two common current trends are reactive systems embedded in an environment and integrated multicomponent architectures. As performance engines, these advanced systems give rise to new learning problems—both in the sense of new opportunities and new difficulties. This chapter discusses new problems for machine learning. Classical problem-solving systems are typically consisted of a single component with a limited range of objectives and capabilities. Some current research efforts adopt a more holistic, synergistic approach involving integrated architectures with a broader scope of objectives and capabilities. These architectures integrate multiple performance components or multiple styles of reasoning. New issues arise within the context of integrated architectures, which engender new requirements and opportunities for machine learning.

[1]  Scott W. Bennett Reducing Real-world Failures of Approximate Explanation-based Rules , 1990, ML.

[2]  Smadar Kedar,et al.  The Blind Leading the Blind: Mutual Refinement of Approximate Theories , 1991, ML.

[3]  Monte Zweben,et al.  Learning Search Control for Constraint-Based Scheduling , 1990, AAAI.

[4]  Mark Drummond,et al.  A representation of action and belief for automatic planning systems , 1987 .

[5]  Prasad Tadepalli,et al.  Lazy ExplanationBased Learning: A Solution to the Intractable Theory Problem , 1989, IJCAI.

[6]  Steve A. Chien Using and Refining Simplifications: Explanation-Based Learning of Plans in Intractable Domains , 1989, IJCAI.

[7]  Richard Waldinger,et al.  Achieving several goals simultaneously , 1977 .

[8]  Leslie Pack Kaelbling,et al.  Integrated Agent Architectures: Benchmark Tasks and Evaluation Metrics , 1990 .

[9]  Allen Newell,et al.  R1-Soar: An Experiment in Knowledge-Intensive Programming in a Problem-Solving Architecture , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Michael Hucka,et al.  Correcting and Extending Domain Knowledge using Outside Guidance , 1990, ML.

[11]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[12]  Tom M. Mitchell,et al.  Representation and Use of Explicit Justifications for Knowledge Base Refinements , 1985, IJCAI.

[13]  Gerald DeJong,et al.  Active Explanation Reduction: An Approach to the Multiple Explanations Problem , 1988, ML.

[14]  Amy L. Lansky,et al.  Reactive Reasoning and Planning , 1987, AAAI.

[15]  James A. Hendler,et al.  Planning in Uncertain, Unpredictable or Changing Environments , 1990 .

[16]  Ajay Gupta,et al.  Explanation-based Failure Recovery , 1987, AAAI.

[17]  Amy L. Lansky,et al.  A Procedural Logic , 1985, IJCAI.

[18]  Kristian J. Hammond Learning to Anticipate and Avoid Planning Problems through the Explanation of Failures , 1986, AAAI.

[19]  Richard Fikes,et al.  Learning and Executing Generalized Robot Plans , 1993, Artif. Intell..

[20]  Jack Mostow,et al.  Failsafe - A Floor Planner that Uses EBG to Learn from Its Failures , 1987, IJCAI.

[21]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[22]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[23]  Mark Drummond,et al.  Goal Ordering in Partially Ordered Plans , 1989, IJCAI.

[24]  John L. Bresina,et al.  Anytime Synthetic Projection: Maximizing the Probability of Goal Satisfaction , 1990, AAAI.

[25]  Smadar Kedar,et al.  Tradeoffs in the utility of learned knowledge , 1992 .

[26]  Smadar Kedar,et al.  The entropy reduction engine: integrating planning, scheduling, and control , 1991, SGAR.

[27]  Tom M. Mitchell,et al.  Becoming Increasingly Reactive , 1990, AAAI.

[28]  Mordechai Ben-Ari,et al.  The Temporal Logic of Branching Time , 1981, POPL.

[29]  Pat Langley,et al.  A design for the ICARUS architecture , 1991, SGAR.

[30]  Oren Etzioni,et al.  Explanation-Based Learning: A Problem Solving Perspective , 1989, Artif. Intell..

[31]  Leslie Pack Kaelbling,et al.  Goals as Parallel Program Specifications , 1988, AAAI.

[32]  Mark Drummond,et al.  Situated Control Rules , 1989, KR.

[33]  Leslie Pack Kaelbling,et al.  An Architecture for Intelligent Reactive Systems , 1987 .

[34]  Stanley J. Rosenschein,et al.  Synthesizing Information-Tracking Automata from Environment Descriptions , 1989, KR.