"225775" . . . . . "978-989-8425-40-9" . "Reactive Layer in AGI Agent"@en . . "AI, AGI, agent architecture, cognitive architecture, reactive agent, situation discrimination"@en . "P(ME 949)" . "1"^^ . "This article presents basic mechanisms of cognition working in AGI agent. I argue that reactive behavior is the baseline of intelligence ? it is the base component working and it can be further extended to produce more intelligent agents. Mechanisms employed at reactive level enable the agent to develop behavior which both explores and exploits the environment with the purpose of receiving highest reward possible. Three fundamental mechanisms are intertwined ? action selection, action value estimation and situation discrimination. Whole process of adaptation is completely unsupervised and depends only on reward received from environment. Some technical details of implementation of given mechanisms (BAGIB agent) are described together with implications to other planned parts of ?AGI-compliant? architecture. Discussed are several challenges we encounter in AGI, which are not present in usually narrow and domain-limited approach to AI."@en . "SciTePress - Science and Technology Publications" . "1"^^ . "Reactive Layer in AGI Agent" . "6"^^ . . . "Reactive Layer in AGI Agent"@en . . "2011-01-28+01:00"^^ . "RIV/49777513:23520/11:43898519" . . . . "ICAART 2011" . . "Reactive Layer in AGI Agent" . . . "\u0158\u00EDm, It\u00E1lie" . "[0F8B8A9D9DEC]" . "23520" . . "Bene\u0161, Vil\u00E9m" . . . "Set\u00FAbal" . . "This article presents basic mechanisms of cognition working in AGI agent. I argue that reactive behavior is the baseline of intelligence ? it is the base component working and it can be further extended to produce more intelligent agents. Mechanisms employed at reactive level enable the agent to develop behavior which both explores and exploits the environment with the purpose of receiving highest reward possible. Three fundamental mechanisms are intertwined ? action selection, action value estimation and situation discrimination. Whole process of adaptation is completely unsupervised and depends only on reward received from environment. Some technical details of implementation of given mechanisms (BAGIB agent) are described together with implications to other planned parts of ?AGI-compliant? architecture. Discussed are several challenges we encounter in AGI, which are not present in usually narrow and domain-limited approach to AI." . "RIV/49777513:23520/11:43898519!RIV12-MSM-23520___" . . .