Search for dissertations about: "Reward learning"
Showing result 16 - 20 of 66 swedish dissertations containing the words Reward learning.
-
16. Safe, human-like, decision-making for autonomous driving
Abstract : Autonomous driving technology can significantly improve transportation by saving lives and social costs and increasing traffic efficiency and availability. Decision-making is a critical component of driving ability. Complex traffic environments and interactions between road users bring about many challenges in decision-making. READ MORE
-
17. Modeling Biochemical Network Involved in Striatal Dopamine Signaling
Abstract : In this thesis, I studied the molecular integration of reward-learning related neuromodulatory inputs by striatal medium-sized projection neurons (MSNs) using mass-action kinetic modeling.It is known that, in reward learning, an unexpected reward results in transient elevation in dopamine (peak) whereas omission of an expected reward leads to transient dopamine decrease (dip). READ MORE
-
18. Efficient Communication via Reinforcement Learning
Abstract : Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication. This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load. READ MORE
-
19. Appetite-regulating peptides and natural rewards: emphasis on ghrelin and glucagon-like peptide-1
Abstract : Evolutionary conserved natural behaviors, such as foraging and sexual behaviors, are strongly associated with reward processes. Brain areas important for reward processes include, but are not limited to, the nucleus accumbens (NAc) shell, the ventral tegmental area (VTA), the laterodorsal tegmental area (LDTg) and the nucleus of the solitary tract (NTS). READ MORE
-
20. Analysis of Attacks on Controlled Stochastic Systems
Abstract : In this thesis, we investigate attack vectors against Markov decision processes anddynamical systems. This work is motivated by the recent interest in the researchcommunity towards making Machine Learning models safer to malicious attacks. READ MORE