| Next revision | Previous revision |
| public:t-720-atai:atai-25:task-environments [2025/01/06 17:49] – created thorisson | public:t-720-atai:atai-25:task-environments [2025/01/06 17:52] (current) – [The Physical World & AI Research] thorisson |
|---|
| | \\ State | **s<sub>t</sub> in V<sub>t</sub>**. A set of variables **x** with a set of values, specified to some particular precision (with constraints, e.g. error bounds), for relevant to a //World//. \\ For all practical purposes, in any complex World "State" refers by default to a sub-state, since it is a practical impossibility to know its full state (values of the complete set of variables) of a world; there will always be a vastly higher number of "don't care" variables than the variables listed for e.g. a //Goal State// (a //State// associated with a //Goal//). || | | \\ State | **s<sub>t</sub> in V<sub>t</sub>**. A set of variables **x** with a set of values, specified to some particular precision (with constraints, e.g. error bounds), for relevant to a //World//. \\ For all practical purposes, in any complex World "State" refers by default to a sub-state, since it is a practical impossibility to know its full state (values of the complete set of variables) of a world; there will always be a vastly higher number of "don't care" variables than the variables listed for e.g. a //Goal State// (a //State// associated with a //Goal//). || |
| | | \\ State \\ definition | **s<sub>t</sub> in V<sub>t</sub>** \\ where \\ **{ x<sub>l</sub>, x<sub>u</sub> } | {x<sub>l</sub> =< x =< x<sub>u</sub>}** \\ defines lower (**x<sub>l</sub>**) and upper (**x<sub>u</sub>**) bounds on acceptable range for each **x** to count towards the State, respectively. | | | | \\ State \\ definition | **s<sub>t</sub> in V<sub>t</sub>** \\ where \\ **{ x<sub>l</sub>, x<sub>u</sub> } | {x<sub>l</sub> =< x =< x<sub>u</sub>}** \\ defines lower (**x<sub>l</sub>**) and upper (**x<sub>u</sub>**) bounds on acceptable range for each **x** to count towards the State, respectively. | |
| | Exposable Variables | Variables in **V** that are measurable and/or manipulatable //in principle//. || | | Exposable Variables | Variables in **V** that are measurable and/or manipulable //in principle//. || |
| | Observable Variables | Variables in **V** that can be measured for a particular interval in time are //observable// during that interval. || | | Observable Variables | Variables in **V** that can be measured for a particular interval in time are //observable// during that interval. || |
| | Manipulatable Variables | Variables in **V** whose value can be affected, either directly or indirectly (by an //Agent// or something else). || | | Manipulatable Variables | Variables in **V** whose value can be affected, either directly or indirectly (by an //Agent// or something else). || |
| | Physical World | The field of physics has been systematically studying the physical world since the ancient Greeks. Over 2000 years later physics is now the most advanced scientific field of all of science. Any proper scientific theory of anything must ultimately rest on its shoulders. | | | Physical World | The field of physics has been systematically studying the physical world since the ancient Greeks. Over 2000 years later physics is now the most advanced scientific field of all of science. Any proper scientific theory of anything must ultimately rest on its shoulders. | |
| | \\ What is it? | Physics seeks to uncover the "ultimate" rules which determine how the universe behaves, including life, intelligence and everything else. \\ No (general or limited) intelligence in a complex environment such as the physical world can be granted access to a full set of axioms of the system it’s controlling, let alone the ⟨agent,environment⟩ tuple, and thus the behavior of a practical generally intelligent artificial agent as a whole simply cannot be captured formally. (see [[http://alumni.media.mit.edu/~kris/ftp/AGI16_growing_recursive_self-improvers.pdf|Steunebrink et al 2016]]) | | | \\ What is it? | Physics seeks to uncover the "ultimate" rules which determine how the universe behaves, including life, intelligence and everything else. \\ No (general or limited) intelligence in a complex environment such as the physical world can be granted access to a full set of axioms of the system it’s controlling, let alone the ⟨agent,environment⟩ tuple, and thus the behavior of a practical generally intelligent artificial agent as a whole simply cannot be captured formally. (see [[http://alumni.media.mit.edu/~kris/ftp/AGI16_growing_recursive_self-improvers.pdf|Steunebrink et al 2016]]) | |
| | Useful AI | To be useful, an AI must **do** something. Ultimately, to be of any use, it must do something in the //physical// world, be it building skyscrapers, auto-generating whole movies from scratch, doing experimental science or inventing the next AI. | | | Useful AI | To be useful, an AI must //**do**// something. Ultimately, to be of any use, it must do so in the //**physical world**//, be it building skyscrapers, auto-generating whole movies from scratch, doing experimental science, or inventing the next AI. | |
| | What this means | A key target environment of the present work is the physical world. | | | What this means | A key target environment of the present work is the physical world. | |
| | Uncertainty | Since any agent in the physical universe will never know //everything:// Some things will always be uncertain. | | | Uncertainty | Since any agent in the physical universe will never know //everything:// Some things will always be uncertain. | |
