Search
Skip to Search Results- 1Al Onazi, Mona Moraybed
- 1Alvarado, Laura
- 1Armstrong, Kieran
- 1Atrazhev, Peter
- 1Austin, James A.
- 1Bakshi, Rita.
-
Fall 2013
This thesis presents new algorithms for dealing with large scale reinforcement learning problems. Central to this work is the Atari 2600 platform, which acts as both a rich evaluation framework and a source of challenges for existing reinforcement learning methods. Three contributions are...
-
Spring 2010
Client sexual advances may be a common occurrence in therapy, yet there is little information available with strategies for managing them. In hope of initiating a dialogue, five female therapists’ experiences were examined for possible insights. Informal semi-structured interviews provided data...
-
Fall 2010
Non-Player Character (NPC) behaviors in today’s computer games are mostly generated from manually written scripts. The high cost of manually creating complex behaviors for each NPC to exhibit intelligence in response to every situation in the game results in NPCs with repetitive and artificial...
-
Immediate and Long-term Effects of Exercise Rehabilitation on Daily Physical Activity of Patients with Cardiopulmonary Disorders
DownloadSpring 2016
It is well known that there is an inverse relationship between physical activity (PA) and mortality in patients with cardiopulmonary disorders. Consequently, PA is considered the core component of cardiopulmonary rehabilitation programs. Despite the health benefits, the adherence to regular PA...
-
Spring 2023
The purpose of this dissertation was to explore, identify and address gaps in exercise oncology evidence-based care for individuals with cancer, with a specific focus on implementation of cancer-specific exercise programming. Further understanding is needed regarding the poor rates of reported...
-
Fall 2021
A common scientific challenge for putting a reinforcement learning agent into practice is how to improve sample efficiency as much as possible with limited computational or memory resources. Such available physical resources may vary in different applications. My thesis introduces some approaches...
-
Spring 2019
Disabling events such as stroke affect millions of people worldwide, causing a need for efficient and functional rehabilitation therapies in order for patients to regain motor function for reintegration back into their normal lives. Rehabilitation regimes often involve performing exercises that...
-
Fall 2017
Model-free off-policy temporal-difference (TD) algorithms form a powerful component of scalable predictive knowledge representation due to their ability to learn numerous counter- factual predictions in a computationally scalable manner. In this dissertation, we address and overcome two...
-
Instrumenting and Validating a Vibrotactile Device to Assess and Rehabilitate Dynamic Seated Balance
DownloadFall 2017
Tools that effectively assess and train dynamic seated balance are critical for enhancing functional independence and reducing risk of secondary health complications in the elderly and individuals with neuromuscular impairments. On the one hand, current assessment tools quantify changes in the...