document

Gradient based adversarial domain randomization

Koning, Gijs (author)

Recent advancements in differential simulators offer a promising approach to enhancing the sim2real transfer of reinforcement learning (RL) agents by enabling the computation of gradients of the simulator’s dynamics with respect to its parameters. However, the application of these gradients is often limited to specific scenarios. In this thesis,...

master thesis 2024

document

Language Assistance in Reinforcement Learning in Dynamic Environments

van Leeuwen, Sander (author)

Language is an intuitive and effective way for humans to communicate. Large Language Models (LLMs) can interpret and respond well to language. However, their use in deep reinforcement learning is limited as they are sample inefficient. State-of-the-art deep reinforcement learning algorithms are more sample efficient but cannot understand...

master thesis 2023

document

Replacing the acquisition function in Bayesian optimization by a neural network: How effectively do meta-learned acquisition functions in Bayesian optimization perform when optimizing for control variates of unknown functions, as compared to BO with standard acquisition functions

Ramezani, Shayan (author)

Bayesian Optimization (BO) has demonstrated significant utility across numerous applications. However, due to it being designed as a universal optimizer, its performance can often be suboptimal in specialized environments. To overcome this issue, research has been conducted into the application of transfer learning for enhancing BO performance...

bachelor thesis 2023

document

Effects of Partial Observability Solver Methods on Training and Final Policies in Autonomous Driver RL: How do different methods for dealing with partial observability in the environment influence training and the robustness of final policies under various testing conditions?

Çil, Ata (author)

Autonomous driving is a complex problem that can potentially be solved using artificial intelligence. The complexity stems from the system's need to understand the surroundings and make appropriate decisions. However, there are various challenges in constructing such a sophisticated system. One of the main challenges is to make the agent learn...

bachelor thesis 2023

document

Evaluating robustness of deep reinforcement learning for autonomous driving: Effects of domain randomization on training and robustness

Bayram, Ege (author)

Deep reinforcement learning has been a topic of research in recent years and has been expanding into the domain of autonomous driving. As autonomous driving is likely to involve people, such as daily commuters, it is necessary to ensure the machine will perform well enough in real-life environments not to put anyone at risk. There exist possible...

bachelor thesis 2023

document

Evaluating Robustness of Deep Reinforcement Learning for Autonomous Driving: How does entropy maximization affect the training and robustness of final policies under various testing conditions?

Ortal, Bartu (author)

This research paper aims to investigate the effect of entropy while training the agent on the robustness of the agent. This is important because robustness is defined as the agent's adaptability to different environments. A self-driving car should adapt to every environment that it is being used in since a mistake could cost someone's life....

bachelor thesis 2023

document

Effects of action space discretization and DQN extensions on algorithm robustness and efficiency: How do the discretization of the action space and various extensions to the well-known DQN algorithm influence training and the robustness of final policies under various testing conditions?

Sözüdüz, Mehmet (author)

Reinforcement Learning (RL) has gained atten-tion as a way of creating autonomous agents for self-driving cars. This paper explores the adap- tation of the Deep Q Network (DQN), a popular deep RL algorithm, in the Carla traffic simulator for autonomous driving. It investigates the influ- ence of action space discretization and DQN ex-<br/...

bachelor thesis 2023

document

An empirical analysis of entropy search in batch bayesian optimisation: A comprehensive study of function shape, batch size, noise level, and dimensionality impact on information-theoretic methods

Hautelman, Alex (author)

Bayesian optimisation is a rapidly growing area of research that aims to identify the optimum of the black-box function, as it strategically directs the optimisation process towards promising regions. This paper provides an overview of the theoretical background used by the Entropy Search algorithms under study, mainly Predictive Entropy Search,...

bachelor thesis 2023

document

Comparative Analysis of Exploration Algorithms in Deep Reinforcement Learning for Autonomous Driving: How does epsilon-greedy, random network distillation, bootstrapped DQN affect training and the robustness of final policies under various testing conditions in autonomous driving?

Sozen, Efe (author)

Autonomous driving is a rapidly evolving field that aims to enhance road safety and reduce accidents through the use of advanced software and hardware technologies. Reinforcement learning (RL) combined with deep neural networks has emerged as a promising approach for training autonomous agents. This research paper investigates three exploration...

bachelor thesis 2023

document

Parallel cost-aware optimization of multidimensional black-box functions

Sihlovec, Oliver (author)

Scientific problems are often concerned with optimization of control variables of complex systems, for instance hyperparameters of machine learning models. A popular solution for such intractable environments is Bayesian optimization. However, many implementations disregard dynamic evaluation costs associated with the optimization procedure....

bachelor thesis 2023

document

DMQL: Deep Maximum Q-Learning: Combatting Relative Overgeneralisation in Deep Independent Learners using Optimism and Similarity

Dam, Erwin (author)

Various pathologies can occur when independent learners are used in cooperative Multi-Agent Reinforcement Learning. One such pathology is Relative Overgeneralisation, which manifests when a suboptimal Nash Equilibrium in the joint action space of a problem is preferred over an optimal Equilibrium. Approaches exist to combat relative...

master thesis 2022

document

Deep Exploration by Planning With Uncertainty in Deep Model Based Reinforcement Learning

Oren, Yaniv (author)

Deep, model based reinforcement learning has shown state of the art, human-exceeding performance in many challenging domains. <br/>Low sample efficiency and limited exploration remain however as leading obstacles in the field. <br/>In this work, we incorporate epistemic uncertainty into planning for better exploration.<br/>We develop a low-cost...

master thesis 2022

document

Reinforcement learning with domain-­specific relational inductive biases: Using Graph Neural Networks and domain knowledge

Vester, Erik (author)

Reinforcement Learning (RL) has been used to successfully train agents for many tasks, but generalizing to a different task - or even unseen examples of the same task - remains difficult. In this thesis, Deep Reinforcement Learning (DRL) is combined with Graph Neural Networks (GNNs) and domain knowledge, with the aim of improving the...

master thesis 2021

document

Formal Verification in Uncertain POMDPs

Neerhoff, Niels (author)

Recurrent neural networks (RNNs) have emerged as an effective method for policy learning in partially observable Markov Decision Processes (POMDPs). However, a major drawback of RNN-based policies is the difficulty to formally verify behavioural specifications, e.g. with regard to reachability and expected cost. In accordance with previous work,...

master thesis 2021

document

Reinforcement Learning for Switching of Semiautomated Vehicles Under Uncomfortable Driving Situations

Uğurlu, Ceren (author)

Over the last two decades, autonomous driving has progressed from science fiction to a real possibility and rapidly developing. However, autonomous driving technology has significant weaknesses and is not safe in unexpected conditions. As a result, automobile manufacturers insist that the driver remains in the driver's seat even while the...

bachelor thesis 2021

document

Reinforcement Learning for Switching Control of Semi-automated Vehicles with Driver Fatigue

Uğurlu, Irem (author)

Automated driving is a rapidly growing technology nowadays. Semi-automated driving is a subpart of automated driving which has multiple driving modes where both driver and automated module can take control. But full safety and comfort guarantees cannot still be given to the drivers. In this project, research has been done to ensure driver safety...

bachelor thesis 2021

document

Optimizing driving entity switching of semi-automated vehicles under automation degradation

Bakos, Csanád (author)

Transitioning to use automated vehicles is a gradual process. Until full automation capabilities are developed there is a need to mediate which driving entity - human or autonomous driving system (ADS) - should be in control depending on the circumstances. This research aims at investigating the switching between manual and automated driving in...

bachelor thesis 2021

document

Safe Reinforcement Learning by Shielding for Autonomous Vehicles

Zoon, Job (author)

In the past few years, there has been much research in the field of Autonomous Vehicles (AV). If AVs are implemented in our daily lives, this could have many advantages. Before this can happen, safe driver models need to be designed which control the AVs. One technique that is suitable to create these models is Reinforcement Learning (RL). A...

master thesis 2021

document

Towards optimizing dual-mode fleet routing and parcel allocation

van der Tas, Veerle (author)

More and more parcels are delivered all over the world, by numerous carriers. Collaboration between couriers can benefit both companies and their customers, as it has the potential to reduce cost and reduce the number of couriers stopping at the same location. Furthermore, autonomous driving is gradually picking up traction opening up another...

master thesis 2020

document

Population-based Active Learning for Black-Box Regression

van Deursen, Max (author)

Many applications employ models to represent real-life environments efficiently. To allow these models to be realistic it is commonly fitted using a dataset containing labeled samples. When obtaining a label for a sample from the environment is expensive, it is key that the dataset contains only those samples that aid in providing a realistic...

master thesis 2020