03953ntm a22005417i 4500 000701125 CZ-PrVSE 20230909171012.0 m d cr n|||||||||| 230909s2023 xr fsbm 000 0 eng d NEZPRACOVANÝ IMPORT ABA006 cze ABA006 ABA006 rda Zeman, Petr ISIS:135631 dis Assessing Policy Optimization agents using Algorithmic IQ test eng Assessing Policy Optimization agents using Algorithmic IQ test / Petr Zeman 2023 ?? stran : digital, PDF soubor Vedoucí práce: Ondřej Vadinský Diplomová práce (Ing.)—Vysoká škola ekonomická v Praze. Fakulta informatiky a statistiky, 2023 Obsahuje bibliografii Textový (vysokoškolská kvalifikační práce) Rok obhajoby 2023 This thesis briefly introduces the history and ideology behind the formalised evaluation of intelligence before focusing on the workings of Algorithmic Intelligence Quotient test. As AIQ is closely related to the Reinforcement Learning framework, the following chapter is dedicated to the principles of this framework and introduces some of the popular agents before focusing more in-depth on the agents I have chosen for implementation: Vanilla Policy Gradient and Proximal Policy Optimization. The practical part of this thesis first introduces the history of the prototypical implementation of the Algorithmic Intelligence Quotient and a description of how its code work. This is closely followed by my update of the code base from Python 2 to Python 3, fixes for the code on the Windows operating system, the introduction of a system for logging a failure of an agent and a few other minor tweaks. Next, the thesis focuses on the complexities in introducing agents based on modern Reinforcement Learning architectures into the AIQ test. As AIQ works with environments inverse to the modern standards of OpenAI Gym and its variations, it was necessary to transform them into a state compatible with the AIQ test. The agents are tested to find good default values of a newly introduced parameter before using various statistical methods to compare the new agents against each other and then against originally implemented agents by using the acquired data. Due to its similarity to other existing benchmarks of implemented agents, the results of the comparison between newly implemented agents support the viability of AIQ as an evaluation tool. The results of the comparison to the initially implemented agents give interesting insight into various agents’ intelligence. Způsob přístupu: Internet znalostní a webové technologie [obor dipl. práce] diplomové práce fd132022 czenas master's theses eczenas Artifficial Intelligence Quotient test Reinforcement Learning Policy Gradient agents Agent Intelligence Evaluation Vanilla Policy Gradient Proximal Policy Optimization Vadinský, Ondřej ISIS:43066 ths Berka, Petr, 1959- jn20001103427 opn Vysoká škola ekonomická v Praze. Fakulta informatiky a statistiky kn20010709399 dgg https://insis.vse.cz/zp/80035/podrobnosti VŠKP v InSIS https://insis.vse.cz/zp/80035 Hlavní práce https://insis.vse.cz/zp/80035/posudek/vedouci Hodnocení vedoucího https://insis.vse.cz/zp/80035/posudek/oponent/79626 Oponentura https://insis.vse.cz/zp/80035/priloha/26613 Přiloha k práci https://insis.vse.cz/zp/80035/podrobnosti dc:identifier NEPOSILAT VSKP vse80035 230907 80035