| Next revision | Previous revision |
| public:t-720-atai:atai-24:agents_and_control [2024/01/30 14:12] – created thorisson | public:t-720-atai:atai-24:agents_and_control [2024/04/29 13:33] (current) – external edit 127.0.0.1 |
|---|
| |
| | {{ :public:t-720-atai:abstract-agent.png?250 }} | | | {{ :public:t-720-atai:abstract-agent.png?250 }} | |
| | An abstraction of a controller: A set of //processes// <m>P</m> that can receive an input, <m>i_t~in~I</m>, produced by and selected from a task-environment, current state <m>S</m>, at least one goal <m>G</m> (implicit or explicit - see table below) and output <m>o_t~in~O</m> in the form of atomic actions (selected from a set of atomic possible outputs <m>O</m>), that (in the limit) achieve goal(s) G. | | | An abstraction of a controller: A set of //processes// **P** that can receive an input, **i_t~in~I**, produced by and selected from a task-environment, current state **S**, at least one goal **G** (implicit or explicit - see table below) and output **o_t~in~O** in the form of atomic actions (selected from a set of atomic possible outputs **O**), that (in the limit) achieve goal(s) G. | |
| | The internals of a controller for the complex, adaptive control of a situated agent is referred to as //cognitive architecture//. | | | The internals of a controller for the complex, adaptive control of a situated agent is referred to as //cognitive architecture//. | |
| | Any practical, operational controller is //embodied//, in that it interacts with its environment through interfaces whereby its internal computations are turned into //physical actions// of some form or other. Input <m>i~in~I</m> enters via //measuring devices// or //**sensors**//, and <m>o_t~in~O</m> exits the controller via //**effectors**//. | | | Any practical, operational controller is //embodied//, in that it interacts with its environment through interfaces whereby its internal computations are turned into //physical actions// of some form or other. Input **i~in~I** enters via //measuring devices// or //**sensors**//, and **o_t~in~O** exits the controller via //**effectors**//. | |
| |
| \\ | \\ |
| \\ | \\ |
| |
| =====What is an 'agent'?===== | =====What is an 'agent' ?===== |
| \\ | \\ |
| \\ | \\ |
| | How Can That Be Done? | How can an AI architecture learn not only multiple co-dependent control pipelines, but also how they may be relevant in some situations and not others, as well as how their setpoints may change depending on context? | | | How Can That Be Done? | How can an AI architecture learn not only multiple co-dependent control pipelines, but also how they may be relevant in some situations and not others, as well as how their setpoints may change depending on context? | |
| | Models | Conant & Ashby showed in [[http://cleamc11.vub.ac.be/books/Conant_Ashby.pdf|1970]] that any good controller of a system //must harbor a **model**// of that system. \\ We will address //models// in the SYMBOLS, MODELS, CAUSATION sprint (see Canvas modules). | | | Models | Conant & Ashby showed in [[http://cleamc11.vub.ac.be/books/Conant_Ashby.pdf|1970]] that any good controller of a system //must harbor a **model**// of that system. \\ We will address //models// in the SYMBOLS, MODELS, CAUSATION sprint (see Canvas modules). | |
| | Agent complexity | Determined by <m>I chi P chi O</m>, not just <m>P, i,</m> or <m>o</m>. | | | Agent complexity | Determined by **I chi P chi O**, not just **P, i,** or **o**. | |
| | Agent action complexity potential | \\ Potential for <m>P</m> to control combinatorics of, or change, <m>o</m>, beyond initial <m>i</m> (at "birth"). | | | Agent action complexity potential | \\ Potential for **P** to control combinatorics of, or change, **o**>, beyond initial **i** (at "birth"). | |
| | Agent input complexity potential | \\ Potential for <m>P</m> to structure <m>i</m> in post-processing, and to extend <m>i</m>. | | | Agent input complexity potential | \\ Potential for **P** to structure <m>i</m> in post-processing, and to extend **i**. | |
| | Agent <m>P</m> complexity potential | \\ Potential for <m>P</m> to acquire and effectively and efficiently store and access past <m>i</m> (learning); potential for <m>P</m> to change <m>P</m>. | | | Agent **P** complexity potential | \\ Potential for **P** to acquire and effectively and efficiently store and access past **i** (learning); potential for **P** to change **P**. | |
| | Agent intelligence potential | Potential for <m>P</m> to coherently coordinate all of the above to improve its own ability to use its resources, acquire more resources, in light of drives (top-level goals). | | | Agent intelligence potential | Potential for **P** to coherently coordinate all of the above to improve its own ability to use its resources, acquire more resources, in light of drives (top-level goals). | |
| |
| \\ | \\ |
| ====Reactive ("Feedback") Agent Architecture==== | ====Reactive ("Feedback") Agent Architecture==== |
| |
| | Feedback | Reacts to measurements. Change happens in light of a received measurement, in which case a control signal <m>v</m> can be produced //after// perturbations of <m>v</m> happens, so that the output of the plant <m>o</m> can catch up with the change. | | | Feedback | Reacts to measurements. Change happens in light of a received measurement, in which case a control signal **v** can be produced //after// perturbations of <m>v</m> happens, so that the output of the plant **o** can catch up with the change. | |
| | What it requires | This requires data from sensors. | | | What it requires | This requires data from sensors. | |
| | Signal Behavior | When reacting to a time-varying signal <m>v</m> the frequency of change, the possible patterns of change, and the magnitude of change of <m>v</m>; latency and jitter can produce unstoppable fluctuations. | | | Signal Behavior | When reacting to a time-varying signal **v** the frequency of change, the possible patterns of change, and the magnitude of change of **v**; latency and jitter can produce unstoppable fluctuations. | |
| | Architecture | Largely fixed for the entire lifetime of the agent. \\ Agent may learn but acts only in reaction to experience (no prediction). | | | Architecture | Largely fixed for the entire lifetime of the agent. \\ Agent may learn but acts only in reaction to experience (no prediction). | |
| | Learning reactive control | \\ Associating reactions to situations. | | | Learning reactive control | \\ Associating reactions to situations. | |
| | The Challenge | Learning requires repeated direct experimentation. Unless we know beforehand which signals cause perturbations in <m>o</m> are dangerous the controller may destroy itself. In task-domains where the number of available signals is vastly greater than the controller's search resources, it may take an unacceptable time for the controller to find good associations for doing its work. | | | The Challenge | Learning requires repeated direct experimentation. Unless we know beforehand which signals cause perturbations in **o** are dangerous the controller may destroy itself. In task-domains where the number of available signals is vastly greater than the controller's search resources, it may take an unacceptable time for the controller to find good associations for doing its work. | |
| |
| \\ | \\ |
