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 273 for “"reward function"”.
-
Stress and Reward Function in Concurrent Depression and Chronic Cannabis Use
… with poor depression symptom course and functional outcomes in MDD. The endocannabinoid system through which cannabis acts is implicated in the regulation of stress responses and reward processing underlying anhedonia, which may be putative processes through which depression outcomes are …
-
Characterizing Reward Function During Social Feedback: Associations with Anhedonia in Socially Anxious Adolescents
… study aimed to: (1) Characterize markers of reward sensitivity during periods of social stress using a well validated social feedback paradigm; (2) Evaluate clinical relations between reward markers and anhedonia; and (3) Investigate if elevated levels of baseline prior exposure to stress …
-
The Role of the Dopamine D1-D2 Receptor Heteromer in Brain Reward Function: Relevance to Drug Addiction and Depression
… the expression of proteins implicated in reward in the nucleus accumbens, such as calcium calmodulin kinase II (CaMKII) and brain derived neurotrophic factor (BDNF), a finding which may be of relevance in neuropsychiatric disorders that exhibit altered reward perception such as addiction …
-
Investigation into changes of the serotonin transporter (5-HTT) gene promoter in association with in vivo prefrontal 5-HTT availability and reward function in human obesity
… psychopathology and to possess regulatory functions on human in vivo 5-HTT availability. However, data on a direct relation between 5-HTTLPR and in vivo 5-HTT availability have been inconsistent. Additional factors such as epigenetic modifications of 5-HTTLPR might contribute to this …
-
Advanced Motor Control Using TD3 Model-Free Reinforcement Learning
… The study aims to address a significant gap in reward function design, specifically the lack of emphasis on speed error in RL-based PMSM control. A modified reward function that penalizes speed deviations is proposed, incentivizing accurate speed tracking while maintaining energy efficiency and …
-
EFFECTIVENESS OF PROXIMAL POLICY OPTIMIZATION METHODS FOR NEURAL PROGRAM INDUCTION
… architecturedesigned to emulate the functionality of a traditional computer. A version of the NVM called NVM-RL supports reinforcement learning based on standard policy gradient methods as a mechanism for performing neural program induction. In this thesis, I modified NVM-RL using one …
-
A flexible approach for optimal rewards in multi-agent reinforcement learning problems
Defining a reward function that, when optimized, results in rapid acquisition of an optimal policy, is one of the most challenging tasks involved in applying reinforcement learning algorithms. The behavior learned by agents is directly related to the reward function they are using. Existing work on …
-
Partial identifiability and misspecification in inverse reinforcement learning
… Reinforcement Learning (IRL) is to infer a reward function <em>R</em> from a policy π. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a given policy; this means that the reward function is only …
-
Knowledge and Ignorance in Reinforcement Learning
… three: the state-space/transition model, the reward function, and the observation model. In this thesis, I present a framework for studying how the state of knowledge or uncertainty of each component affects the Reinforcement Learning process. I focus on the reward function and the observation …
-
Reinforcement learning beyond rewards : decision-making in the language of visitation distributions
… finding a policy that maximizes the cumulative reward in the environment. The generality of the RL framework rests on the reward function being a universal way to specify a decision-making task to an agent. While this notion of the universality of reward function has been debated, reward …
-
Thresholded linear bandits
… one method is to exploit the structure of the reward function. However, the presence of an unknown threshold component makes previously known algorithms for structured bandits unsuitable. Moreover, the threshold introduces a discontinuity to the reward function, making the problem significantly …
-
Safety-aware apprenticeship learning
… in the AI community that finding a good reward function for reinforcement learning is extremely challenging. Apprenticeship learning (AL) is a class of “learning from demonstration” techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent …
-
Modelling motorcyclist-pedestrian interactions using inverse reinforcement learning
… over time. The utility is expressed by the reward function, which provides insights into road users’ behaviour in conflict interactions and can be recovered from real road user trajectories. For this study, video data from a busy and congested intersection in Shanghai, China is used. …
-
Reinforcement learning tuning of sliding mode control for an underactuated autonomous surface vehicle
… RL agent results. Results from varying the PPO reward function suggested tradeoffs with performance, where improved metrics aligned with specific emphasis in the reward function.
-
INTELLIGENT CONTROL AND LEARNING OF ROBOTS INTERACTING WITH ENVIRONMENTS
… Impedance adaptation is developed using a cost function or a reward function to describe the interaction performance, and impedance parameters to be adjusted to maximize the reward function. For the proposed reference adaptation, the cost function is minimized using trajectory parametrization …
-
TOWARDS HUMAN-CENTRIC AI: INVERSE REINFORCEMENT LEARNING MEETS ALGORITHMIC FAIRNESS
… that uses a novel kernel to explore the reward function space efficiently. The second work introduces SCALES, a framework that translates various fairness principles into fair decisions by translating them to a combination of utility, non-causal and causal components which are, in turn, …
-
Robust and Flexible Reward Modeling for LLM Alignment
… ways to align language models is by designing a reward function that measures alignment with human values, and training the language model to maximize this reward. In this thesis, we focus on two approaches reward design: reward design from external feedback signals and reward learning from human …
-
Look-ahead reinforcement learning : an application for load balancing network trafficc
… To evaluate our work, we firstly perform a functional evaluation to discuss different re ward functions for load balancing using reinforcement learning. Secondly, we evaluate the elephant flow identification, discussing the impact of looking to elephant flows on reinforcement learning …
-
Vulnerabilities in Maximum Entropy Inverse Reinforcement Learning under Adversarial Demonstrations
… on the availability of a well-specified reward function, the design of which is often a significant challenge. Inverse Reinforcement Learning (IRL) offers a compelling solution to this problem by enabling an agent to infer an underlying reward function from expert demonstrations. This …
-
Interactively learning to summarise timelines by reinforcement learning
… meet the user’s demands. I define a compound reward function that can update automatically according to the received feedback to ensure topical coherence, factual consistency and linguistic fluency of the generated summaries. The system use this reward function to adjust its output content via …
Page 1 of 14