While Artificial Intelligence (AI) is making giant steps, it is also raising concerns about its trustworthiness, due to the fact that widely-used black-box models cannot be exactly understood by humans. One of the ways to improve humans’ trust towards AI is to use interpretable AI models, i.e., models that can be thoroughly understood by humans, and thus trusted. However, interpretable AI models are not typically used in practice, as they are thought to be less performing than black-box models. This is more evident in Reinforce- ment Learning, where relatively little work addresses the problem of performing Reinforce- ment Learning with interpretable models. In this thesis, we address this gap, proposing methods for Interpretable Reinforcement Learning. For this purpose, we optimize Decision Trees by combining Reinforcement Learning with Evolutionary Computation techniques, which allows us to overcome some of the challenges tied to optimizing Decision Trees in Reinforcement Learning scenarios. The experimental results show that these approaches are competitive with the state-of-the-art score while being extremely easier to interpret. Finally, we show the practical importance of Interpretable AI by digging into the inner working of the solutions obtained.

This thesis investigates the integration of 3D printing with clay and post-tensioning techniques, seeking to establish a structural reinforcement system for 3D-printed clay pieces. The primary goal is to marry the inherent flexibility of clay with the strength provided by post-tensioning, thereby introducing a novel construction paradigm. The culmination of this research involves the design and realization of a pavilion or architectural structure, serving as a practical demonstration of the proposed system's viability in real-world applications. Through an exhaustive review of existing projects and the development of an innovative construction methodology, this study contributes to the evolving landscape of sustainable and adaptable architectural solutions. / Master of Architecture / In this research, I delved into the intricate realm of construction, specifically exploring the possibilities when 3D printing technology meets clay, an age-old material. The main thrust was to devise a system that fortifies 3D printed clay pieces using a technique known as post-tensioning—transforming them into not just visually captivating structures but also robust in their structural integrity. Picture a pavilion or architectural marvel materializing from this fusion. This research isn't confined to theoretical musings; it's about crafting tangible structures that redefine the horizons of sustainable and adaptable architecture. Join me in navigating this journey where clay seamlessly converges with the avant-garde!

This dissertation investigates the problem of representation discovery in discrete Markov decision processes, namely how agents can simultaneously learn representation and optimal control. Previous work on function approximation techniques for MDPs largely employed hand-engineered basis functions. In this dissertation, we explore approaches to automatically construct these basis functions and demonstrate that automatically constructed basis functions significantly outperform more traditional, hand-engineered approaches. We specifically examine two problems: how to automatically build representations for action-value functions by explicitly incorporating actions into a representation, and how representations can be automatically constructed by exploiting a pre-specified task hierarchy. We first introduce a technique for learning basis functions directly in state-action space. The approach constructs basis functions using spectral analysis of a state-action graph which captures the underlying structure of the state-action space of the MDP. We describe two approaches to constructing these graphs and evaluate the approach on MDPs with discrete state and action spaces. We show how our approach can be used to approximate state-action value functions when the agent has access to macro-actions: actions that take more than one time step and have predefined policies. We describe how the state-action graphs can be modified to incorporate information about the macro-actions and experimentally evaluate this approach for SMDPs with discrete state and action spaces. Finally, we describe how hierarchical reinforcement learning can be used to scale up automatic basis function construction. We extend automatic basis function construction techniques to multi-level task hierarchies and describe how basis function construction can exploit the value function decomposition given by a fixed task hierarchy. We demonstrate that combining task hierarchies with automatic basis function construction allows basis function techniques to scale to larger problems and leads to a significant speed-up in learning.

No description available.

No description available.

No

No description available.

The main idea of this thesis is to define and formulate the role of cognitive control in cognitive dynamic systems and complex networks in order to control the directed flow of information. A cognitive dynamic system is based on Fuster's principles of cognition, the most basic of which is the so-called global perception-action cycle, that the other three build on. Cognitive control, by definition, completes the executive part of this important cycle. In this thesis, we first provide the rationales for defining cognitive control in a way that it suits engineering requirements. To this end, the novel idea of entropic state and thereby the two-state model is first described. Next, on the sole basis of entropic state and the concept of directed information flow, we formulate the learning algorithm as the first process of cognitive control. Most importantly, we show that the derived algorithm is indeed a special case of the celebrated Bellman's dynamic programming. Another significant key point is that cognitive control intrinsically differs from the generic dynamic programming and its approximations (commonly known as reinforcement learning) in that it is stateless by definition. As a result, the main two desired characteristics of the derived algorithm are described as follows: a) it is convergent to optimal policy, and b) it is free of curse of dimensionality. Next, the predictive planning is described as the second process of cognitive control. The planning process is on the basis of shunt cycles (called mutually composite cycles herein) to bypass the environment and facilitate the prediction of future global perception-action cycles. Our results demonstrate predictive planning to have a very significant improvement to the functionality of cognitive control. We also deploy the explore/exploit strategy in order to apply a simplistic form of executive attention. The thesis is then expanded by applying cognitive control into two different applications of practical importance. The first one involves cognitive tracking radar, which is based on a benchmark example and provides the means for testing the theory. In order to have a frame of reference, the results are compared to other cognitive controllers, which use traditional Q-learning and the method of dynamic optimization. In both cases, the new algorithm demonstrates considerable improvement with less computational load. For the second application, the problem of observability in stochastic complex networks has been picked due to its importance in many practical situations. Having known cognitive control theory and its significant performance, the idea here is to view the network as the environment of a cognitive dynamic system; thereby, cognitive dynamic system with the cognitive controller plays a supervisory role over the network. The proposed methodology differs from the state-of-the-art in the literature in two accounts: 1) stochasticity both in modelling as well as monitoring processes, and 2) complexity in terms of edge density. We present several examples to demonstrate the information processing power of cognitive control in this context too. The thesis will finish by drawing line for future research in three main directions. / Thesis / Doctor of Philosophy (PhD)

<p> Two experiments, involving 140 subjects, were performed to study the effects of two partial reinforcement variables on measures of stimulus control in extinction. Pigeons were required to make a fixed number of responses ranging from 1 to 64) to terminate discrete trial presentations and were rewarded on a predetermined percentage (ranging from 100% to 25%) of those completed trials. Generalization tests involved repeated nonreinforced presentations of the training stimulus and a new stimulus until animals ceased responding. Stimulus control measured by differences or ratios of responding to the two stimuli increased as response requirement increased. The percent of trials reinforced had no significant effect on either measure of control. Within-trial analyses showed that maximum stimulus control is exerted over the first response, some control continues to be exerted over successive responses, and there is a tendency for control to increase near the end of the requirement. Implications of the research were discussed.</p> / Thesis / Doctor of Philosophy (PhD)

Previous studies, typically with children, have used delay-tolerance training to treat problem behavior maintained by access to tangibles. This often involves physical prompting and waiting rather than exchanging, two practices that may not be possible or relevant to adults with intellectual disabilities (ID). For many adults with ID in residential settings, exchanging items, rather than waiting per se, may be evocative for problem behavior. In the current study, I evaluated an exchange program to treat problem behavior maintained by access to tangibles for adults diagnosed with ID at a residential facility. I measured the latency to exchange low- and high-preference items following a request for the item and the individual's problem behaviors. Results demonstrated that the exchange program increased relinquishing of an item while decreasing the rate of problem behavior. This analysis provides another method to treat problem behavior maintained by access to tangibles for adults without using physical prompting.