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 24 for “"Intrinsic Reward"”.
-
Comparative Analysis of Intrinsic Reward-Based Reinforcement Learning Algorithms
… often struggle in tasks with sparse or delayed rewards, since they receive little guidance about which actions to pursue. This thesis investigates how adding intrinsic rewards can help address that issue. We focus on three main methods: Count-Based bonuses, where states are hashed and infrequent …
-
Reimagining Exploration: Theoretical Insights and Practical Advancements in Policy Gradient Methods
… focus on policy parameterization choices and reward-shaping methods with intrinsic exploration bonuses. First, we analyze the influence of policy stochasticity on the optimization process. We formulate direct policy optimization within the optimization-by-continuation framework, which involves …
-
Full-time community college faculty with doctorates
… included feelings of self-satisfaction and intrinsic reward in addition to "fit" with personal and family needs. Professional motivators included enjoyment of teaching along with the existing challenges of teaching in the community college.
-
Directed Exploration In Deep Reinforcement Learning Through Optimism
… and based on learning from positive or negative rewards. One of the main dilemmas in any Reinforcement Learning task is the exploration-exploitation tradeoff: The question of when the agent should exploit known rewards and when it should take actions that it believes are suboptimal to learn more …
-
Leader Self-Disclosure Depth: The Consequences of Leader’s Personal Disclosure for Followers
… disclosers with many advantages such as higher intrinsic reward and improved interpersonal relations. Previous research on self-disclosure has mostly been developed within the context of close relationships (e.g., intimate partners) or strangers (e.g., who are not expected to interact again), …
-
Reinforcement learning at the edge of chaos
… updates pre-trained policies with a stabilising intrinsic reward function. This approach improves global stability without retraining from scratch and is compatible with any existing reinforcement learning controllers. Together, these contributions tackle a key limitation in current reinforcement …
-
ROBUST COUNTERFACTUAL LEARNING FOR CLINICAL DECISION-MAKING USING ELECTRONIC HEALTH RECORDS
… and limited knowledge of the clinician's intrinsic reward function and environment dynamics. This motivates the need to tackle uncertainty and enable improved clinical policy generalization via context-based policy learning. We propose counterfactual frameworks to tackle the highlighted …
-
Flow as a metastable brain state: evidence from EEG microstates, entropy-based complexity, and electromagnetic modulation
… by deep absorption, effortless control, and intrinsic reward, yet it’s neurophysiological mechanisms remain incompletely understood. This thesis integrates psychological theory, electrophysiology, and electromagnetic field (EMF) models of brain function to conceptualize flow as a metastable …
-
Knowledge workers and their relationships with organisations
… but also that job challenge, problem solving, intrinsic reward and team identification were of importance to both groups of knowledge workers. This thesis presents an examination of knowledge workers’ perceptions of work, organisations and people management practices in the granulation and …
-
Risk homeostasis theory in simulated environments
… is based on the simulation of physical risk with intrinsic reward rather than a 'points pay-off'. The second aim of the thesis is to examine a number of predictions made by RHT through the use of this alternative methodology. Since the pseudo-experimental design and post hoc analysis of …
-
Negotiating kendo capital and gendered identity in a Japanese sports university kendo club
… a ‘bigendered identity’ and experience intrinsic reward in kendo more so than men as they are bound to a separate sphere of oppressive systems and articulations. Albeit a result of patriarchy, women do experience agency and can positively create their own raison d'être through the …
-
A comparison of relationships between older adults and their close friends and adult children.
… including strength of the relationship, intrinsic and utilitarian rewards, and relationship strain, and to examine the differential impact of these variables on life satisfaction. Subjects were 44 widowed women over 65 years of age, who were retired and had at least one adult child not …
-
Modulating Reinforcement- Learning Parameters Using Agent Emotions
… a computational model of emotion to provide an intrinsic reward function, the task can be shifted to optimisation of emotional feedback, allowing more high-level goals to be defined. While of most interest in a general, not necessarily competitive, social setting on a continuing task, such a …
-
Causality-inspired reinforcement learning: state abstractions, exploration, and representations
… affect the transition of each factor) and in reward functions (which state factors determine task success). These causal structures enable RL agents to learn accurate dynamics and reward models, and to design hierarchical policies for solving complex, long-horizon tasks sample-efficiently …
-
Motives and Values Associated with Participation in Intercollegiate Student-Athlete Community Service: Implications for Athletics Department Leadership
… by being required, motivation to volunteer with intrinsic reward, motivation for career experience, and motivation through participation in a group/organization. These motivation factors were used as dependent variables and statistically significant relationships occurred when comparing …
-
Reinforcement Learning Based Systems Modeling and Decision-Making
… enhance the model performance, the concept of intrinsic motivation is introduced into the proposed framework by proposing a unique intrinsic reward. Second, we focus on the droplet pinch-off behaviors which affect the quality of final printed products in IJP in Chapter 3. Specifically, we …
-
Learning navigation policies with deep reinforcement learning
… in learning control policies in terminal reward settings, as this scenario requires the least amount of human priors and would thus largely automate the training of artificial decision-making agents. As structured and guided exploration becomes vital in this case, we again question the …
-
Towards Optimistic, Imaginative, and Harmonious Reinforcement Learning in Single-Agent and Multi-Agent Environments
… agent’s underestimation of the expected future reward, i.e. the state-value function. To alleviate the issue we propose to enhance the agent’s state-value function approximator with more global information. In visual navigation, we do so by learning the spatio-temporal relationship between …
-
Obedience-based Multi-Agent Cooperation for Sequential Social Dilemmas
… Reinforcement Learning (MARL) settings by intrinsically rewarding agents for obeying the commands of other agents. At every timestep, agents exchange commands through a cheap-talk channel. During the following timestep, agents are rewarded both for taking actions that conform to commands …
-
Exploration of dentists’ characteristics associated with caring for disadvantaged patients using a mixed-methods approach.
… relieving pain and improving their wellness; 4) ‘Intrinsic reward’; the personal gain in receiving simple, unexpected rewards that made a difference; 5) ‘Resilience’; the overarching theme, derived from personal experiences and challenges of the work environment. In Stage 2, 1523 questionnaires …
Page 1 of 2