| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| public:t-720-atai:atai-19:lecture_notes_w2-2 [2020/03/13 18:38] – [Reflective Agent Architecture] thorisson | public:t-720-atai:atai-19:lecture_notes_w2-2 [2024/04/29 13:33] (current) – external edit 127.0.0.1 |
|---|
| ====Predictive Agent Architecture==== | ====Predictive Agent Architecture==== |
| | Architecture | Largely fixed for the entire lifetime of the agent. \\ Subsumes the reactive agent architecture, adding that the agent may learn to predict and can use predictions to steer its actions. | | | Architecture | Largely fixed for the entire lifetime of the agent. \\ Subsumes the reactive agent architecture, adding that the agent may learn to predict and can use predictions to steer its actions. | |
| | Super-simple | These have fixed topology; mostly hard-wired control and perception. | | | Super-simple | These have fixed topology; mostly hard-wired control and perception. Prediction limited to one or a few hard-wired topics. No learning. | |
| | Simple | These are above the complexity of super-simple architectures. Deterministic connections between components with small memory, where the memory makes learning and prediction possible. Example: Nest "intelligent" thermostat. | | | Simple | Deterministic connections between components with small memory, where the memory makes learning and prediction possible. Example: Nest "intelligent" thermostat. | |
| | Complex | Grossly modular architecture (< 30 modules) with multiple relationships at more than one level of control detail (LoC). \\ Examples: No obvious ones come to mind. | | | Complex | Grossly modular architecture (< 30 modules) with multiple relationships at more than one level of control detail (LoC). \\ Example: Predictive management for powergrid of a state or nation. | |
| | Super-Complex | Large number of modules (> 30) at various sizes, each with multiple relationships to others, at more than one LoC. \\ Examples: No obvious ones come to mind. | | | Super-Complex | Large number of modules (> 30) at various sizes, each with multiple relationships to others, at more than one LoC. \\ Examples: No obvious ones come to mind. | |
| | Bottom Line | It is difficult but possible to integrate predictive learning and behavior control into complex agent architectures using constructionist approaches (hand-coding); better methodologies are needed. | | | Bottom Line | It is difficult but possible to integrate predictive learning and behavior control into complex agent architectures using constructionist approaches (hand-coding); better methodologies are needed. | |
| \\ | \\ |
| ====Reflective Agent Architecture==== | ====Reflective Agent Architecture==== |
| | Architecture | Architecture changes over the history of the agent. \\ Subsumes features of reactive and predictive architectures, adding introspection (reflection) and some form of (meta-)reasoning (as necessary for managing the introspection). | | | Architecture | Architecture changes over the history of the agent. Can demonstrate cognitive growth (cognitive developmental stages). \\ Subsume features of reactive and predictive architectures, adding introspection (reflection) and some form of (meta-)reasoning (as necessary for managing the introspection). | |
| | Super-simple | . | | | Super-simple | These are above the complexity of super-simple architectures. | |
| | Simple | These are above the complexity of simple architectures. | | | Simple | These are above the complexity of simple architectures. | |
| | Complex | Complexity stems from interaction among parts, many of which are generated by the system at runtime and whose complexity may mirror some parts of the task-environment (if task-environment is complex, and lifetime is long, the resulting control structures are likely to be complex as well). \\ Examples: NARS, AERA. | | | Complex | Complexity stems from interaction among parts, many of which are generated by the system at runtime and whose complexity may mirror some parts of the task-environment (if task-environment is complex, and lifetime is long, the resulting control structures are likely to be complex as well). \\ Examples: NARS, AERA. | |
| | | Transversal Integration | A general-purpose system must tightly and finely coordinate a host of skills, including their acquisition, transitions between skills at runtime, how to combine two or more skills, and transfer of learning between them over time at many levels of temporal and topical detail. | | | | Transversal Integration | A general-purpose system must tightly and finely coordinate a host of skills, including their acquisition, transitions between skills at runtime, how to combine two or more skills, and transfer of learning between them over time at many levels of temporal and topical detail. | |
| |
| | \\ |
| | \\ |
| | \\ |
| | \\ |
| |
| 2019(c)K. R. Thórisson | 2019(c)K. R. Thórisson |
