Curiosity-driven algorithm for reinforcement learning
Authors
Date
2019Copyright
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
One problem of current Reinforcement Learning algorithms is finding a balance between exploitation of existing knowledge and exploration for a new experience. Curiosity exploration bonus has been proposed to address this problem, but current implementations are vulnerable to stochastic noise inside the environment. The new approach presented in this thesis utilises exploration bonus based on the predicted novelty of the next state. That protects exploration from noise issues during training. This work also introduces a new way of combining extrinsic and intrinsic rewards. Both improvements help to overcome a number of problems that Reinforcement Learning had until now.
Keywords
Metadata
Show full item recordCollections
- Pro gradu -tutkielmat [29376]
Related items
Showing items with similar title or keywords.
-
Artificial Intelligence and Computational Science
Neittaanmäki, Pekka; Repin, Sergey (Springer, 2022)In this note, we discuss the interaction between two ways of scientific analysis. The first (classical) way is known as Mathematical Modeling (MM). It is based on a model created by humans and presented in mathematical ... -
Evolutionary Algorithms and Metaheuristics : Applications in Engineering Design and Optimization
Greiner, David; Periaux, Jacques; Quagliarella, Domenico; Magalhaes-Mendes, Jorge; Galván, Blas (Hindawi Publishing Corporation, 2018) -
Strategic cyber threat intelligence : Building the situational picture with emerging technologies
Voutilainen, Janne; Kari, Martti (Academic Conferences International, 2020)In 2019, e-criminals adopted new tactics to demand enormous ransoms from large organizations by using ransomware, a phenomenon known as “big game hunting.” Big game hunting is an excellent example of a sophisticated and ... -
On Attacking Future 5G Networks with Adversarial Examples : Survey
Zolotukhin, Mikhail; Zhang, Di; Hämäläinen, Timo; Miraghaei, Parsa (MDPI AG, 2023)The introduction of 5G technology along with the exponential growth in connected devices is expected to cause a challenge for the efficient and reliable network resource allocation. Network providers are now required to ... -
Practices and Infrastructures for Machine Learning Systems : An Interview Study in Finnish Organizations
Muiruri, Dennis; Lwakatare, Lucy Ellen; Nurminen, Jukka K.; Mikkonen, Tommi (Institute of Electrical and Electronics Engineers (IEEE), 2022)Using interviews, we investigated the practices and toolchains for machine learning (ML)-enabled systems from 16 organizations across various domains in Finland. We observed some well-established artificial intelligence ...