2026-07-09T04:19:59Zhttps://ebiltegia.mondragon.edu/oai/request

oai:ebiltegia.mondragon.edu:20.500.11984/145712026-06-18T06:15:48Zcom_20.500.11984_1143com_20.500.11984_14090col_20.500.11984_1148

Enhancing World Models with Specialized Prediction Networks for Reinforcement Learning Mellado Ibañez, Álvaro Arana-Arexolaleiba, Nestor Vázquez, Juan Ignacio Machine Learning Reinforcement Learning World Models Training robots in the real-world using reinforcement learning is both expensive and risky. World Models—a simulated environment that mirrors real-world conditions—have been proved to offer an alternative to real-world training. Such simulation-based training not only reduces costs significantly but also reduces the dependency from real-world testing. While previous studies focus on single-network architectures that predict state, reward, and episode termination as a single output, this research proposes a different approach by creating a structure based on specialized prediction networks for each of the aforementioned elements. During the experiment, several simulated environments were used. The main results obtained showed that the specialized-network World Models were capable of learning the environment’s dynamics adequately, and that the proposed architecture outperformed single-network configurations by more effectively capturing these dynamics. Finally, future directions are included on possible ways to enhance World Models efficiency. 2026-06-17T13:04:55Z 2026-06-17T13:04:55Z 2025 978-3-032-08461-3 https://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=200664 https://hdl.handle.net/20.500.11984/14571 eng © 2025 Springer Springer