| Next revision | Previous revision |
| public:t-720-atai:atai-19:lecture_notes_w3 [2019/09/04 17:32] – created thorisson | public:t-720-atai:atai-19:lecture_notes_w3 [2024/04/29 13:33] (current) – external edit 127.0.0.1 |
|---|
| | World | A set of constraints that a set of Environments have in common. | | | World | A set of constraints that a set of Environments have in common. | |
| | Task | A Problem (or Goal) that can be assigned. Typically comes with Instructions (guide to Solution production). | | | Task | A Problem (or Goal) that can be assigned. Typically comes with Instructions (guide to Solution production). | |
| | Problem | A Goal with (all) relevant constraints (≈ negative goals, requirements). | | | Problem | An unachieved Goal with (all) relevant constraints (≈ negative goals, requirements). | |
| | Goal | A (future, sub-) State to be attained, plus (optional) constraints on the Goal (if well defined). | | | Goal | A (future, sub-) State to be attained, plus (optional) constraints on the Goal (if well defined). | |
| | State | A particular set of values (with error bounds) that a subset of variables in the Environment can take. | | | State | A particular set of values (with error bounds) that a subset of variables in the Environment can take. | |
| | Solution | The set of (atomic) actions that can achieve a Goal. May be at various levels of specificity. | | | Solution | The set of (atomic) actions that can achieve a Goal. May be at various levels of specificity. | |
| | Solution Space | The amount of variation allowed on a State while still counting as a Solution to a Problem. | | | Solution Space | The amount of variation allowed on a State while still counting as a Solution to a Problem. | |
| | Action | The changes an Agent can make to variables relevant to a Task-Environment. | | | Action | The changes an Agent can make to variables relevant to a Task-Environment. Atomic action that can be meaningfully referred to when constructing and modifying Plans. | |
| | Plan | A partial way to accomplish a Task. | | | Plan | A partial (description of a) way to accomplish a Task. A set of sequential Actions that may be performed in an Environment to achieve a Goal. | |
| | Instructions | Partial Plan for accomplishing a Task, typically given to an Agent along with a Task by a Teacher. | | | Instructions | Partial Plan for accomplishing a Task, typically given to an Agent along with a Task by a Teacher. | |
| | Teacher | The Agent assigning a Task to another Agent (student), optionally in charge of Instructions. | | | Teacher | The assignor (Agent or entity) assigning a Task to another Agent (student), optionally in charge of Instructions. | |
| | Task Constraint | Limits the allowed Solution Space for a Problem. Can help or hinder a Task to be achieved. | | | Task Constraint | Limits the allowed Solution Space for a Problem. Can help or hinder a Task to be achieved. | |
| | Plan | One or more Actions that may be performed in an Environment to achieve a Goal. \\ Typically a sequence of Actions is required. | | |
| | Action | Atomic action that can be meaningfully referred to when constructing and modifying Plans. | | |
| |
| |
| \\ | \\ |
| \\ | \\ |
| |
| |
| ====Limited Time & Energy (LTE)==== | ====Limited Time & Energy (LTE)==== |
| |
| {{public:t-720-atai:time-scales-newell-et-al.png}} | {{public:t-720-atai:time-scales-newell-et-al.png}} |
| | From Card, Moran & Newell et al. //The Psychology of Human-Computer Interaction// (1983). |
| \\ | \\ |
| \\ | \\ |
| \\ | \\ |
| \\ | \\ |
| ====What Kind of Worlds shold AGI systems handle?==== | ====What Kind of Worlds should AGI systems handle?==== |
| | Novelty | Novelty is encountered by controllers in Worlds where the World is vastly larger in variety than the controller can store in a lookup table. Interaction between Environmental elements (subsets of <m>V_E</m>) produces phenomena of a different //**kind**// than the elements that interact. | | | Novelty | Novelty is encountered by controllers in Worlds where the World is vastly larger in variety than the controller can store in a lookup table. Interaction between Environmental elements (subsets of <m>V_E</m>) produces phenomena of a different //**kind**// than the elements that interact. | |
| | Balance | The Worlds we are interested in strike a balance between completely dynamic and completely static. \\ They also strike a balance between completely deterministic and completely random; some regularity must exist at a level that is observable initially by a learning agent. | | | Balance | The Worlds we are interested in strike a balance between completely dynamic and completely static. \\ They also strike a balance between completely deterministic and completely random; some regularity must exist at a level that is observable initially by a learning agent. | |
| \\ | \\ |
| \\ | \\ |
| ====What Kind of Task-Environments do AGI sysetms target?==== | ====What Kind of Task-Environments do AGI Systems Target?==== |
| | Environment | Large number of potentially relevant variables. | | | Worlds | Complex, intricate worlds, large number of variables (relative to the system's CPU and memory). \\ Complexity lies somewhere between randomness and regularity. \\ Many levels of temporal and spatial detail. \\ Ultimately, any system worthy of being called "AGI" must be successful operation in the physical world. | |
| | Task | Ditto. | | | Environments | Somewhere between random and static. Dynamic; large number of variables (relative to the system's CPU and memory capacity). \\ Many levels of temporal and spatial detail. | |
| | Solutions | Medium number. | | | Tasks | Dynamic; large number of variables (relative to the system's CPU and memory capacity). \\Underspecified. | |
| | Instructions | Optionally. | | | Goals | Multiple goals can easily be specified. | |
| | | Solutions | New solutions can be found. | |
| \\ | \\ |
| \\ | \\ |
| |
| |
| ====How it Hangs Together: Worlds, Environments, Tasks, Goals==== | ====How it Hangs Together: Worlds, Environments, Tasks, Goals==== |
| \\ | \\ |
| |
| | 2019(c)K.R.Thorisson |
| |
| //EOF// | //EOF// |
