Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 84 for “"Atari"”.
-
Single-player to Two-player Knowledge Transfer in Atari 2600 Games
… examines the proposed idea in ten different Atari 2600 environments using the Atari 2600 RAM as the input state. The advantages of using transfer learning from a single-player training process over training in a two-player setting from scratch are discussed, and the results are demonstrated …
-
The Effectiveness of Electronic Games (Atari) Reinforcers for Increasing Appropriate Behavior in Handicapped Children
Ten subjects ranging from 9 to 16 years in age with IQ's ranging from 23 to 62 were randomly selected as contingent or noncontingent subjects for two experiments. Five subjects received contingent access to two electronic games for performance within a specified learning session, while five …
-
A resource guide to physical science/physics software for the Apple II, Atari, Pet, and TRS-80
… microcomputers: Apple II, Pet, TRS-80, and Atari. The resource guide will consist of the following: 1. A list and description of the high school physical science/physics software available for AISD teachers in the various Resource Centers. 2. A list and description of the commercial software …
-
Supervised attention from natural language feedback for reinforcement learning
… Revenge, the most difficult game in the Atari Arcade suite. However, our final framework demonstrates the incompatibility of language in the Atari suite in a supervised attention setting. The ultimate result showed that as long as the agent’s position in the observation was clear, the …
-
Online Decision Mamba
… in-depth evaluations on MuJoCo (OpenAI Gym) and Atari benchmarks, comparing ODM against state-of-the-art offline and online baselines—including Decision Mamba (DM) and ODT. Our results show that ODM achieves competitive or superior performance, with particularly robust gains when initial datasets …
-
Critic-derived shaping in Proximal Policy Optimization
… tasks and performs particularly well on the Atari game Gravitar. Conservative CDAS-0 and CDAS-λ settings in MuJoCo increase mean PPO-normalized final return by around 4–5% above PPO. However, the improvements are environment-dependent; Venture demonstrates how visually prominent but …
-
Hlasový generátor pro pokročilé embedded systémy
… generování hlasového výstupu a analýza programu Atari 520ST Speech Synthesizer V2.0. Jako vhodný embedded systém byla vybrána vývojová deska Raspberry Pi Pico.
-
O inimigo que todos querem ter : videogame e sociedade no Brasil de 1983
… nos meses precedentes ao lançamento oficial do Atari 2600 no Brasil (janeiro a setembro), da Polyvox, e que mencionem videogames, que foram catalogados em um banco de dados construído com linguagem SQL. Na primeira metade do Capítulo 1, analisamos dados levantados sobre anúncios classificados …
-
Hraní her pomocí neuronových sítí
… řízení, hraní tahové hry 2048 a několika Atari her. Jedná se o oblast zpětnovazebního učení. Jako zpětnovazební algoritmus využívající neuronové sítě jsem použil Hluboké Q-učení. Ten jsem pro zvýšení efektivity učení obohatil o několik vylepšení. Mezi vylepšení patří přidání cílové sítě, …
-
Efficient reinforcement learning through variance reduction and trajectory synthesis
… prove their effectiveness through experiments on Atari and MuJoCo environment.
-
Λειτουργία των Τ.Ε.Π., σύστημα διαλογής και ικανοποίηση και χρόνος αναμονής των ασθενών στο Τ.Ε.Π. του Γ.Ν.Α. Λαϊκού
… Satisfaction Scale) που αντλήθηκε απο την έρευνα Atari & Atari (2015), η ικανοποίηση μετρήθηκε με χρήση τετραβάθμιας κλίμακας, όπου το 1 αντιπροσώπευε το «καθόλου ικανοποιημένο»ς και το 4 το «απόλυτα ικανοποιημένος». Τα δεδομένα που χρησιμοποιήθηκαν για την επίτευξη των στόχων της έρευνας ήταν …
-
Addressing stale gradients in asynchronous federated deep reinforcement learning
… results from applying these methods to two Atari-2600 games demonstrate a relative speedup of up to 95\% compared to plain A3C in large and unstable federations.
-
Evolutionary Policy Optimization
… in RL. Experiments on function minimization and Atari benchmarks show that EPO can improve both policy quality and sample efficiency compared to standard PG and EC methods.
-
Leveraging multimodal human cues to enhance robot learning from demonstration
… demonstration types. In the simulated domain of Atari game playing, we also identify that the attention of high-performing but sample inefficient reinforcement learning agents for six different games is most similar to human demonstrator attention for the same game. Based on our findings, we …
-
Design and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agents
… results obtained with OpenAI Gym library-based Atari 2600 video gaming environment demonstrate that the proposed hybrid multi-task learning model is successful in addressing key challenges associated with the performance optimization of deep reinforcement learning agents.
-
Preferential proximal policy optimization in reinforcement learning
… value function. Empirical evaluations across six Atari environments demonstrate that our approach outperforms the baseline (vanilla PPO) across different tested environments, highlighting the value of our proposed method in learning complex environments.
-
I Play To Beat The Machine: Masculinity And The Video Game Industry In The United States
… worldwide instead of the U.S. companies, such as Atari.
-
Adversarial Patch Attacks on Deep Reinforcement Learning Algorithms
… comparable results as FGSM and PGD attack, on Atari and Procgen environments, for DQN and PPO respectively. In addition, We also design Context Re-Constructor to reconstruct state when the state is corrupted by the patch. Based on the reconstructed states, we can identify the patch position and …
-
An Empirical Study on the Efficacy of Evolutionary Algorithms for Automated Neural Architecture Search
… learning to learn control policy for ATARI game playing. Empirical classification results on the NASBench image dataset using different population selection and drop methods for the evolutionary NAS are presented to validate the usefulness of simple evolutionary algorithms in …
Page 1 of 5