Note: Intro -- Theoretical Foundations of Artificial General Intelligence -- Contents -- 1 Introduction: What Is the Matter Here? -- 1.1 The Matter of Artificial General Intelligence -- 1.2 The Matter of Theoretical Foundation -- 1.3 The Matter of Objective -- 1.4 The Matter of Approach -- 1.5 Challenges at the Heart of the Matter -- 1.6 Summary -- Bibliography -- 2 Artificial Intelligence and CognitiveModeling Have the Same Problem -- 2.1 The Intelligence Problem -- 2.1.1 Naming the problem -- 2.1.2 Why the Intelligence Problem is Important -- 2.1.3 The State of the Science -- 2.2 Existing Methods and Standards are not Sufficient -- 2.2.1 Formal linguistics -- 2.2.2 Neuroscience -- 2.2.3 Artificial intelligence -- 2.2.4 Experimental psychology -- 2.3 CognitiveModeling: The Model Fit Imperative -- 2.4 Artificial Intelligence and CognitiveModeling Can Help Each Other -- 2.5 Conclusions -- Bibliography -- 3 Psychometric Artificial General Intelligence: The Piaget-MacGuyver Room -- 3.1 Introduction -- 3.2 More on Psychometric AGI -- 3.2.1 Newell & -- the Neglected Route Toward General Machine Intelligence -- 3.2.2 So, What is Psychometric AGI? -- 3.2.3 Springboard to the Rest of the Present Paper -- 3.3 Descartes' Two Tests -- 3.4 Piaget's View of Thinking & -- The Magnet Test -- 3.5 The LISA model -- 3.6 Analogico-Deductive Reasoning in the Magnet Test -- 3.7 Next Steps -- Bibliography -- 4 Beyond the Octopus: From General Intelligence toward a Human-likeMind -- 4.1 Introduction -- 4.2 Octopus Intelligence -- 4.3 A "Ladder" of Intelligence -- 4.4 Linguistic Grounding -- 4.5 Implications of the Ladder for AGI -- 4.6 Conclusion -- Bibliography -- 5 One Decade of Universal Artificial Intelligence -- 5.1 Introduction -- 5.2 The AGI Problem -- 5.3 Universal Artificial Intelligence -- 5.4 Facets of Intelligence -- 5.5 Social Questions. , 5.6 State of the Art -- 5.7 Discussion -- Epilogue. -- Bibliography -- 6 Deep Reinforcement Learning as Foundation for Artificial General Intelligence -- 6.1 Introduction: Decomposing the AGI Problem -- 6.2 Deep Learning Architectures -- 6.2.1 Overcoming the Curse of Dimensionality -- 6.2.2 Spatiotemporal State Inference -- 6.3 Scaling Decision Making under Uncertainty -- 6.3.1 Deep Reinforcement Learning -- 6.3.2 Actor-Critic Reinforcement Learning Themes in Cognitive Science -- 6.4 Neuromorphic Devices Scaling AGI -- 6.5 Conclusions and Outlook -- Bibliography -- 7 The LIDA Model as a Foundational Architecture for AGI -- 7.1 Introduction -- 7.2 Why the LIDA model may be suitable for AGI -- 7.3 LIDA architecture -- 7.4 Cognitive architectures, features and the LIDA model -- 7.4.1 7.4.1 Ron Sun's Desiderata [53 -- 7.4.2 Newell's functional criteria (adapted from Lebiere and Anderson 2003) -- 7.4.3 BICA table -- 7.5 Discussion, Conclusions -- Bibliography -- 8 The Architecture of Human-Like General Intelligence -- 8.1 Introduction -- 8.2 Key Ingredients of the Integrative Human-Like Cognitive Architecture Diagram -- 8.3 An Architecture Diagram for Human-Like General Intelligence -- 8.4 Interpretation and Application of the Integrative Diagram -- 8.5 Cognitive Synergy -- 8.6 Why Is It So Hard to Measure Partial Progress Toward Human-Level AGI? -- 8.7 Conclusion -- Bibliography -- 9 A New Constructivist AI: From Manual Methods to Self-Constructive Systems -- 9.1 Introduction -- 9.2 The Nature of (General) Intelligence -- 9.3 Constructionist AI: A Critical Look -- 9.4 The Call for a New Methodology -- 9.5 Towards a New Constructivist AI -- 9.5.1 Temporal Grounding -- 9.5.2 Feedback Loops -- 9.5.3 Pan-Architectural Pattern Matching -- 9.5.4 Transparent Operational Semantics -- 9.5.5 Integration and Architecture Metaconstruction -- 9.6 Conclusions. , Acknowledgments -- Bibliography -- 10 Towards an Actual Gödel Machine Implementation: A Lesson in Self-Reflective Systems -- 10.1 Introduction -- 10.2 The Gödel Machine Concept -- 10.3 The Theoretical Foundations of Self-Reflective Systems -- 10.3.1 Basic λ -calculus -- 10.3.2 Constants, Conditionals, Side-effects, and Quoting -- 10.4 Nested Meta-Circular Evaluators -- 10.5 A Functional Self-Reflective System -- 10.6 Discussion -- Bibliography -- 11 Artificial General Intelligence Begins with Recognition: Evaluating the Flexibility of Recognition -- 11.1 Introduction -- 11.2 Evaluating Flexibility -- 11.2.1 The Testing Paradigm -- 11.2.2 Combinatorial Difficulties of Superposition or Mixes -- 11.2.3 "Occluding" Superpositions -- 11.2.4 Counting Tests -- 11.2.5 Binding Tests -- 11.2.6 Binding and The Set-Cover Problem -- 11.2.7 Noise Tests -- 11.2.8 Scoring the Tests -- 11.2.9 Evaluating Algorithms' Resources -- 11.3 Evaluation of Flexibility -- 11.3.1 Superposition Tests with Information Loss -- 11.3.2 Superpositions without loss -- 11.3.3 Counting Tests -- 11.3.4 Binding Scenarios -- 11.3.5 Noise Tests -- 11.3.6 Scoring Tests Together -- 11.3.7 Conclusion from Tests -- 11.4 Summary -- Acknowledgments -- Bibliography -- 12 Theory Blending as a Framework for Creativity in Systems for General Intelligence -- 12.1 Introduction -- 12.2 Productivity and CognitiveMechanisms -- 12.3 Cross-Domain Reasoning -- 12.4 Basic Foundations of Theory Blending -- 12.5 The Complex Plane: A Challenging Historical Example -- 12.6 Outlook for Next Generation General Intelligent Systems -- 12.7 Conclusions -- Bibliography -- 13 Modeling Motivation and the Emergence of Affect in a Cognitive Agent -- 13.1 Introduction -- 13.2 Emotion and affect -- 13.3 Affective states emerging from cognitive modulation -- 13.4 Higher-level emotions emerging from directing valenced affects. , 13.5 Generating relevance: the motivational system -- 13.6 Motive selection -- 13.7 Putting it all together -- Acknowledgments -- Bibliography -- 14 AGI and Machine Consciousness -- 14.1 Introduction -- 14.2 Consciousness -- 14.3 Machine Consciousness -- 14.4 Agent's Body -- 14.5 Interactions with the Environment -- 14.6 Time -- 14.7 FreeWill -- 14.8 Experience -- 14.9 Creativity -- 14.10 Conclusions -- Bibliography -- 15 Human and Machine Consciousness as a Boundary Effect in the Concept Analysis Mechanism -- 15.1 Introduction -- 15.1.1 The Hard Problem of Consciousness -- 15.1.2 A Problem within the Hard Problem -- 15.1.3 An Outline of the Solution -- 15.2 The Nature of Explanation -- 15.2.1 The Analysis Mechanism -- 15.2.2 The Molecular Framework -- 15.2.3 Explanation in General -- 15.2.4 Explaining Subjective Concepts -- 15.2.5 The "That Misses The Point" Objection -- 15.3 The Real Meaning of Meaning -- 15.3.1 Getting to the Bottom of Semantics -- 15.3.2 Extreme Cognitive Semantics -- 15.3.3 Implications -- 15.4 Some Falsifiable Predictions -- 15.4.1 Prediction 1: Blindsight -- 15.4.2 Prediction 2: New Qualia -- 15.4.3 Prediction 3: Synaesthetic Qualia -- 15.4.4 Prediction 4: Mind Melds -- 15.5 Conclusion -- Bibliography -- 16 Theories of Artificial Intelligence -Meta-theoretical considerations -- 16.1 The problem of AI theory -- 16.2 Nature and content of AI theories -- 16.3 Desired properties of a theory -- 16.4 Relations among the properties -- 16.5 Issues on the properties -- 16.6 Conclusion -- Acknowledgements -- Bibliography -- Index.