Recent progress has been made in understanding optimisation dynamics in neural networks trained with full-batch gradient descent with momentum with the uncovering of the edge of stability phenomenon in supervised learning. The edge of stability phenomenon occurs as the leading eigenvalue of the Hessian reaches the divergence threshold of the underlying optimisation algorithm for a quadratic loss, after which it starts oscillating around the threshold, and the loss starts to exhibit local instability but decreases over long time frames. In this work, we explore the edge of stability phenomenon in reinforcement learning (RL), specifically off-policy Q-learning algorithms across a variety of data regimes, from offline to online RL. Our experiments reveal that, despite significant differences to supervised learning, such as non-stationarity of the data distribution and the use of bootstrapping, the edge of stability phenomenon can be present in off-policy deep RL. Unlike supervised learning, however, we observe strong differences depending on the underlying loss, with DQN -- using a Huber loss -- showing a strong edge of stability effect that we do not observe with C51 -- using a cross entropy loss. Our results suggest that, while neural network structure can lead to optimisation dynamics that transfer between problem domains, certain aspects of deep RL optimisation can differentiate it from domains such as supervised learning.

Online reinforcement learning (RL) is increasingly used for realizing adaptive systems in the presence of design time uncertainty. Online RL facilitates learning from actual operational data and thereby leverages feedback only available at runtime. However, Online RL requires the definition of an effective and correct reward function, which quantifies the feedback to the RL algorithm and thereby guides learning. With Deep RL gaining interest, the learned knowledge is no longer explicitly represented, but is represented as a neural network. For a human, it becomes practically impossible to relate the parametrization of the neural network to concrete RL decisions. Deep RL thus essentially appears as a black box, which severely limits the debugging of adaptive systems. We previously introduced the explainable RL technique XRL-DINE, which provides visual insights into why certain decisions were made at important time points. Here, we introduce an empirical user study involving 54 software engineers from academia and industry to assess (1) the performance of software engineers when performing different tasks using XRL-DINE and (2) the perceived usefulness and ease of use of XRL-DINE.

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become popular in AD applications in recent years. However, the performance of existing RL algorithms heavily depends on the diversity of training scenarios. A lack of safety-critical scenarios during the training phase could result in poor generalization performance in real-world driving applications. We propose a novel framework in which the weaknesses of the training set are explored through black-box verification methods. After discovering AD failure scenarios, the RL agent's training is re-initiated via transfer learning to improve the performance of previously unsafe scenarios. Simulation results demonstrate that our approach efficiently discovers safety failures of action decisions in RL-based adaptive cruise control (ACC) applications and significantly reduces the number of vehicle collisions through iterative applications of our method. The source code is publicly available at https://github.com/data-and-decision-lab/self-improving-RL.

The exponential growth of textual data has created a crucial need for tools that assist users in extracting meaningful insights. Traditional document summarization approaches often fail to meet individual user requirements and lack structure for efficient information processing. To address these limitations, we propose Summation, a hierarchical personalized concept-based summarization approach. It synthesizes documents into a concise hierarchical concept map and actively engages users by learning and adapting to their preferences. Using a Reinforcement Learning algorithm, Summation generates personalized summaries for unseen documents on specific topics. This framework enhances comprehension, enables effective navigation, and empowers users to extract meaningful insights from large document collections aligned with their unique requirements.

Deep model-based reinforcement learning methods offer a conceptually simple approach to the decision-making and control problem: use learning for the purpose of estimating an approximate dynamics model, and offload the rest of the work to classical trajectory optimization. However, this combination has a number of empirical shortcomings, limiting the usefulness of model-based methods in practice. The dual purpose of this thesis is to study the reasons for these shortcomings and to propose solutions for the uncovered problems. We begin by generalizing the dynamics model itself, replacing the standard single-step formulation with a model that predicts over probabilistic latent horizons. The resulting model, trained with a generative reinterpretation of temporal difference learning, leads to infinite-horizon variants of the procedures central to model-based control, including the model rollout and model-based value estimation.

Autonomous driving technology has five levels, from L0 to L5. Currently, only the L2 level (partial automation) can be achieved, and there is a long way to go before reaching the final level of L5 (full automation). The key to crossing these levels lies in training the autonomous driving model. However, relying solely on real-world road data to train the model is far from enough and consumes a great deal of resources. Although there are already examples of training autonomous driving models through simulators that simulate real-world scenarios, these scenarios require complete manual construction. Directly converting 3D scenes from road network formats will lack a large amount of detail and cannot be used as training sets. Underground parking garage static scenario simulation is regarded as a procedural content generation (PCG) problem. This paper will use the Sarsa algorithm to solve procedural content generation on underground garage structures.

Heterogeneous Information Networks (HINs) are information networks with multiple types of nodes and edges. The concept of meta-path, i.e., a sequence of entity types and relation types connecting two entities, is proposed to provide the meta-level explainable semantics for various HIN tasks. Traditionally, meta-paths are primarily used for schema-simple HINs, e.g., bibliographic networks with only a few entity types, where meta-paths are often enumerated with domain knowledge. However, the adoption of meta-paths for schema-complex HINs, such as knowledge bases (KBs) with hundreds of entity and relation types, has been limited due to the computational complexity associated with meta-path enumeration. Additionally, effectively assessing meta-paths requires enumerating relevant path instances, which adds further complexity to the meta-path learning process. To address these challenges, we propose SchemaWalk, an inductive meta-path learning framework for schema-complex HINs. We represent meta-paths with schema-level representations to support the learning of the scores of meta-paths for varying relations, mitigating the need of exhaustive path instance enumeration for each relation. Further, we design a reinforcement-learning based path-finding agent, which directly navigates the network schema (i.e., schema graph) to learn policies for establishing meta-paths with high coverage and confidence for multiple relations. Extensive experiments on real data sets demonstrate the effectiveness of our proposed paradigm.

In this study, we explore how Deep Q-Network (DQN) might improve the functionality of multiclass classification algorithms. We will use a benchmark dataset from Kaggle to create a framework incorporating DQN with existing supervised multiclass classification algorithms. The findings of this study will bring insight into how deep reinforcement learning strategies may be used to increase multiclass classification accuracy. They have been used in a number of fields, including image recognition, natural language processing, and bioinformatics. This study is focused on the prediction of financial distress in companies in addition to the wider application of Deep Q-Network in multiclass classification. Identifying businesses that are likely to experience financial distress is a crucial task in the fields of finance and risk management. Whenever a business experiences serious challenges keeping its operations going and meeting its financial responsibilities, it is said to be in financial distress. It commonly happens when a company has a sharp and sustained recession in profitability, cash flow issues, or an unsustainable level of debt.

Text-based games provide a framework for developing natural language understanding and commonsense knowledge about the world in reinforcement learning based agents. Existing text-based environments often rely on fictional situations and characters to create a gaming framework and are far from real-world scenarios. In this paper, we introduce ScriptWorld: a text-based environment for teaching agents about real-world daily chores and hence imparting commonsense knowledge. To the best of our knowledge, it is the first interactive text-based gaming framework that consists of daily real-world human activities designed using scripts dataset. We provide gaming environments for 10 daily activities and perform a detailed analysis of the proposed environment. We develop RL-based baseline models/agents to play the games in Scriptworld. To understand the role of language models in such environments, we leverage features obtained from pre-trained language models in the RL agents. Our experiments show that prior knowledge obtained from a pre-trained language model helps to solve real-world text-based gaming environments. We release the environment via Github: https://github.com/Exploration-Lab/ScriptWorld

Humans perform everyday tasks using a combination of locomotion and manipulation skills. Building a system that can handle both skills is essential to creating virtual humans. We present a physically-simulated human capable of solving box rearrangement tasks, which requires a combination of both skills. We propose a hierarchical control architecture, where each level solves the task at a different level of abstraction, and the result is a physics-based simulated virtual human capable of rearranging boxes in a cluttered environment. The control architecture integrates a planner, diffusion models, and physics-based motion imitation of sparse motion clips using deep reinforcement learning. Boxes can vary in size, weight, shape, and placement height. Code and trained control policies are provided.