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 37 for “"Reward Learning"”.
-
Bayesian nonparametric reward learning from demonstration
Learning from demonstration provides an attractive solution to the problem of teaching autonomous systems how to perform complex tasks. Demonstration opens autonomy development to non-experts and is an intuitive means of communication for humans, who naturally use demonstration to teach others. …
-
Synaptic Control of Dopamine as a Driver of Reward Learning
… (VTADA) neurons fire in a manner consistent with Reward Prediction Error, with better-than-expected and worse-than-expected outcomes correlating with bursts and pauses, respectively. Burst and pause firing dynamics are believed to be responsible for driving associative learning, yet interrogating …
-
Impulsivity and Reward Sensitivity: Attentional and Emotional Factors Underlying Stimulus-Reward Learning
Increased impulsivity and alterations in reward sensitivity co-occur in many psychiatric disorders. Moreover, individuals reporting more impulsive traits are less efficient in learning stimulus-reward associations. This suggests that impulsivity and reward sensitivity may be linked, consistent with …
-
Offline Reward Learning from Human Demonstrations and Feedback: A Linear Programming Approach
… tasks, there is often no known explicit reward function, and the only information available is human demonstrations and feedback data. To infer and shape the underlying reward function from this data, two key methodologies have emerged: inverse reinforcement learning (IRL) and …
-
A new class of neural architectures to model episodic memory : computational studies of distal reward learning
… and is tested on a particular task of distal reward learning. Categorical Neural Semantic Theory informs the architecture design. To experiment upon the computational brain model, embodiment and an environment in which the embodiment exists are simulated. This simulated environment realizes …
-
Behavioral Training of Reward Learning Increases Reinforcement Learning Parameters and Decreases Depression Symptoms Across Repeated Sessions
Background: Disrupted reward learning has been suggested to contribute to the etiology and maintenance of depression. If deficits in reward learning are core to depression, we would expect that improving reward learning would decrease depression symptoms across time. Whereas previous studies have …
-
Anxiety and Anhedonia in Major Depressive Disorder: The Contributing Roles of Neuroticism, Cognitive Control, and Reward Learning
… impaired cognitive control, and blunted reward learning have been suggested to be critical processes involved in MDD, and may help to explain symptoms of anxiety and anhedonia. Using baseline data from individuals with MDD (N=296) in the Establishing Moderators and Biosignatures of …
-
Learning and memory systems supporting decision making in the human brain
… we have learned. In the brain, two prominent learning systems have been identified and each is likely to guide decisions in different ways. Research on decision making has primarily focused on a reward learning system in the striatum. These studies have illuminated the how repeated choices and …
-
The Effects of Self-Relevance on Neural Learning Signals Indexing Attention, Perception, and Learning
… or someone else, participants exhibit larger reward processing signals for themselves. Additionally, attention and perception are biased not only towards one’s self but those related to them. However, the aspect of processing information related to known-others has not been addressed in reward …
-
Biologically inspired computational neural models for motivated behavior, learning, and memory
… of artificial intelligence (AI) and machine learning have vastly expanded in the past decade, with a variety of modern applications, ranging from computer vision to language processing and medical diagnostics. While the majority of AI applications involve data classification, detection, and …
-
Adversarial Inverse Reinforcement Learning with Noisy Observations
<p>Inverse reinforcement learning (IRL) has emerged as a popular approach for training robots from human/expert demonstration, where a learner/robot infers the expert's hidden reward function using the demonstrations and a simulator. We argue that noise is inevitable in certain parts of the …
-
The amygdala in value-guided decision making
… a structure well known for its role in fear and reward learning, but how these mechanisms are used for decision-making is not well understood. Decision-making involves the rapid updating of cue associations as well as the encoding of a value currency, both processes in which the amygdala has been …
-
Behavioral and linguistic markers of craving
… the striatum has been implicated in forming cue-reward associations, striatal-based reward-learning theories suggest such associations should weaken without reinforcement. In contrast, hippocampal-dependent episodic memories are known to strengthen over time through replay and consolidation, …
-
Effects of Priming on Subsequent Associative Memory: Testing Prediction Error and Attentional Accounts
… the model to improve future performance. Thus, learning should be driven by PE. Feedforward and feedback signalling have been widely studied in the fields of reward learning and perception, but although there are strong reasons to expect related processes in memory, less work has been done to …
-
Inferring the Human's Objective in Human Robot Interaction
… for inferring upon the human's objective for Reward Learning and Communicative Shared Autonomy settings. To accomplish this, we first examine state-of-the-art methods for approaching Bayesian Inverse Reinforcement learning where we explore the strengths and weaknesses of current approaches. …
-
Terrain and Adversary-Aware Autonomous Robot Navigation
… aims to implement autonomous robot navigation by learning terrain affordances: traversability (moving quickly) and concealment (staying hidden from an adversary) using the Preference-based Inverse Reward Learning (PbIRL) methodology. The PbIRL methodology reduces the barrier of generating initial …
-
Long-term characterization of the chronic dopamine microelectrode and effect of electrical conditioning
… (DA) is a neurotransmitter involved in movement, reward learning and addiction. Fast-scan cyclic voltammetry (FSCV) has long been an indispensable tool for monitoring real-time DA signaling. Development of polyimide fused silica-encased FSCV microelectrodes have made the technique more suitable …
-
Perceiving the Good: An Agent Relative Account of Desire
… motivational theories, pleasure-based theories, reward/learning accounts, and evaluative models. Ultimately, I argue that none of these theories provides adequate explanation for the metaphysics or phenomenology of desire. After providing arguments against these approaches, I develop my position …
-
Putting 'Dopamine Overdose' To The Test: A Psychopharmacological Investigation in Parkinson's Disease and Healthy Volunteers
… the effects of dopaminergic therapy on stimulus-reward and reversal learning in groups of PD patients that differed in severity of their disease and extent of dopamine deficiency. Learning impairments were found in late-stage PD at baseline and in early-stage PD with dopaminergic therapy, …
-
Being Alone: Social Disconnection in Adolescence
… isolation on psychological state and on threat learning. Chapter three investigates the effects of social isolation on reward responsiveness — including reward seeking and reward learning — integrating computational models of learning. Chapter four leverages ultra-high field 7-Tesla MRI to …
Page 1 of 2