Deep Reinforcement Learning (DRL) systems often tend to overfit to early experiences, a phenomenon known as the primacy bias (PB). This bias can severely hinder learning efficiency and final performance, particularly in complex environments. This paper presents a comprehensive investigation of PB through the lens of the Fisher Information Matrix (FIM). We develop a framework characterizing PB through distinct patterns in the FIM trace, identifying critical memorization and reorganization phases during learning. Building on this understanding, we propose Fisher-Guided Selective Forgetting (FGSF), a novel method that leverages the geometric structure of the parameter space to selectively modify network weights, preventing early experiences from dominating the learning process. Empirical results across DeepMind Control Suite (DMC) environments show that FGSF consistently outperforms baselines, particularly in complex tasks. We analyze the different impacts of PB on actor and critic networks, the role of replay ratios in exacerbating the effect, and the effectiveness of even simple noise injection methods. Our findings provide a deeper understanding of PB and practical mitigation strategies, offering a FIM-based geometric perspective for advancing DRL.

The attribution of the author of an art piece is typically a laborious manual process, usually relying on subjective evaluations of expert figures. However, there are some situations in which quantitative features of the artwork can support these evaluations. The extraction of these features can sometimes be automated, for instance, with the use of Machine Learning (ML) techniques. An example of these features is represented by repeated, mechanically impressed patterns, called punches, present chiefly in 13th and 14th-century panel paintings from Tuscany. Previous research in art history showcased a strong connection between the shapes of punches and specific artists or workshops, suggesting the possibility of using these quantitative cues to support the attribution. In the present work, we first collect a dataset of large-scale images of these panel paintings. Then, using YOLOv10, a recent and popular object detection model, we train a ML pipeline to perform object detection on the punches contained in the images. Due to the large size of the images, the detection procedure is split across multiple frames by adopting a sliding-window approach with overlaps, after which the predictions are combined for the whole image using a custom non-maximal suppression routine. Our results indicate how art historians working in the field can reliably use our method for the identification and extraction of punches.

Lifelike visualizations in design, cinematography, and gaming rely on precise physics simulations, typically requiring extensive computational resources and detailed physical input. This paper presents a method that can infer a system's physical properties from a short video, eliminating the need for explicit parameter input, provided it is close to the training condition. The learned representation is then used within a Graph Network-based Simulator to emulate the trajectories of physical systems. We demonstrate that the video-derived encodings effectively capture the physical properties of the system and showcase a linear dependence between some of the encodings and the system's motion.

Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to expected rewards or search for policies that can maximize a certain performance function. Model-Based algorithms instead, aim to learn an approximation of the underlying model of the RL environment and then use it in combination with planning algorithms. Upside-Down Reinforcement Learning (UDRL) is a novel learning paradigm that aims to learn how to predict actions from states and desired commands. This task is formulated as a Supervised Learning problem and has successfully been tackled by Neural Networks (NNs). In this paper, we investigate whether function approximation algorithms other than NNs can also be used within a UDRL framework. Our experiments, performed over several popular optimal control benchmarks, show that tree-based methods like Random Forests and Extremely Randomized Trees can perform just as well as NNs with the significant benefit of resulting in policies that are inherently more interpretable than NNs, therefore paving the way for more transparent, safe, and robust RL.

Production scheduling is an essential task in manufacturing, with Reinforcement Learning (RL) emerging as a key solution. In a previous work, RL was utilized to solve an extended permutation flow shop scheduling problem (PFSSP) for a real-world production line with two stages, linked by a central buffer. The RL agent was trained to sequence equallysized product batches to minimize setup efforts and idle times. However, the substantial impact caused by varying the size of these product batches has not yet been explored. In this follow-up study, we investigate the effects of varying batch sizes, exploring both the quality of solutions and the training dynamics of the RL agent. The results demonstrate that it is possible to methodically identify reasonable boundaries for the batch size. These boundaries are determined on one side by the increasing sample complexity associated with smaller batch sizes, and on the other side by the decreasing flexibility of the agent when dealing with larger batch sizes. This provides the practitioner the ability to make an informed decision regarding the selection of an appropriate batch size. Moreover, we introduce and investigate two new curriculum learning strategies to enable the training with small batch sizes. The findings of this work offer the potential for application in several industrial use cases with comparable scheduling problems.

A recent method for solving zero-sum partially observable stochastic games (zs-POSGs) embeds the original game into a new one called the occupancy Markov game. This reformulation allows applying Bellman's principle of optimality to solve zs-POSGs. However, improving a current solution requires solving a linear program with exponentially many potential constraints, which significantly restricts the scalability of this approach. This paper exploits the optimal value function's novel uniform continuity properties to overcome this limitation. We first construct a new operator that is computationally more efficient than the state-of-the-art update rules without compromising optimality. In particular, improving a current solution now involves a linear program with an exponential drop in constraints. We then also show that point-based value iteration algorithms utilizing our findings improve the scalability of existing methods while maintaining guarantees in various domains.

Despite the considerable attention given to the questions of \textit{how much} and \textit{how to} explore in deep reinforcement learning, the investigation into \textit{when} to explore remains relatively less researched. While more sophisticated exploration strategies can excel in specific, often sparse reward environments, existing simpler approaches, such as $\epsilon$-greedy, persist in outperforming them across a broader spectrum of domains. The appeal of these simpler strategies lies in their ease of implementation and generality across a wide range of domains. The downside is that these methods are essentially a blind switching mechanism, which completely disregards the agent's internal state. In this paper, we propose to leverage the agent's internal state to decide \textit{when} to explore, addressing the shortcomings of blind switching mechanisms. We present Value Discrepancy and State Counts through homeostasis (VDSC), a novel approach for efficient exploration timing. Experimental results on the Atari suite demonstrate the superiority of our strategy over traditional methods such as $\epsilon$-greedy and Boltzmann, as well as more sophisticated techniques like Noisy Nets.

The rapid expansion of online information from diverse sources and the growing multilingual nature of the web underscore the escalating significance of information retrieval (IR) and recommender systems (RS). Today's web is no longer limited to a single language, but is increasingly rich in multiple languages, mirroring the multilingual capacities of its global users Steichen et al. [2014], Tashu et al. [2023]. This diversity highlights the urgent need for cross-lingual recommender systems. Traditional recommender systems often prioritize content in a single language, sidelining a wealth of multilingual documents that may hold valuable insights. This gap leads to the emergence of cross-language information access, where recommender systems suggest items in different languages based on user queries Lops et al. [2010], Narducci et al. [2016], Salamon et al. [2021]. Machine Learning and Deep Learning, which have significantly impacted language representation and processing, are pivotal to enhancing information retrieval and recommender systems, especially in the realm of document recom-The result presented in this work is based on Eduard-Raul Kontos's bachelor project while he was at the University of Groningen

Reinforcement Learning (RL) has been widely explored in Traffic Signal Control (TSC) applications, however, still no such system has been deployed in practice. A key barrier to progress in this area is the reality gap, the discrepancy that results from differences between simulation models and their real-world equivalents. In this paper, we address this challenge by first presenting a comprehensive analysis of potential simulation parameters that contribute to this reality gap. We then also examine two promising strategies that can bridge this gap: Domain Randomization (DR) and Model-Agnostic Meta-Learning (MAML). Both strategies were trained with a traffic simulation model of an intersection. In addition, the model was embedded in LemgoRL, a framework that integrates realistic, safety-critical requirements into the control system. Subsequently, we evaluated the performance of the two methods on a separate model of the same intersection that was developed with a different traffic simulator. In this way, we mimic the reality gap. Our experimental results show that both DR and MAML outperform a state-of-the-art RL algorithm, therefore highlighting their potential to mitigate the reality gap in RLbased TSC systems.

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously learned tasks. However, determining which source task qualifies as the most appropriate for knowledge extraction, as well as the choice regarding which algorithm components to transfer, represent severe obstacles to its application in reinforcement learning. The goal of this paper is to address these issues with modular multi-source transfer learning techniques. The proposed techniques automatically learn how to extract useful information from source tasks, regardless of the difference in state-action space and reward function. We support our claims with extensive and challenging cross-domain experiments for visual control.