Satellite communication is a key technology in our modern connected world. With increasingly complex hardware, one challenge is to efficiently configure links (connections) on a satellite transponder. Planning an optimal link configuration is extremely complex and depends on many parameters and metrics. The optimal use of the limited resources, bandwidth and power of the transponder is crucial. Such an optimization problem can be approximated using metaheuristic methods such as simulated annealing, but recent research results also show that reinforcement learning can achieve comparable or even better performance in optimization methods. However, there have not yet been any studies on link configuration on satellite transponders. In order to close this research gap, a transponder environment was developed as part of this work. For this environment, the performance of the reinforcement learning algorithm PPO was compared with the metaheuristic simulated annealing in two experiments. The results show that Simulated Annealing delivers better results for this static problem than the PPO algorithm, however, the research in turn also underlines the potential of reinforcement learning for optimization problems.

Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving, which is increasingly applied in diverse driving scenarios. However, driving is a multi-attribute problem, leading to challenges in achieving multi-objective compatibility for current RL methods, especially in both policy execution and policy iteration. On the one hand, the common action space structure with single action type limits driving flexibility or results in large behavior fluctuations during policy execution. On the other hand, the multi-attribute weighted single reward function result in the agent's disproportionate attention to certain objectives during policy iterations. To this end, we propose a Multi-objective Ensemble-Critic reinforcement learning method with Hybrid Parametrized Action for multi-objective compatible autonomous driving. Specifically, a parameterized action space is constructed to generate hybrid driving actions, combining both abstract guidance and concrete control commands. A multi-objective critics architecture is constructed considering multiple attribute rewards, to ensure simultaneously focusing on different driving objectives. Additionally, uncertainty-based exploration strategy is introduced to help the agent faster approach viable driving policy. The experimental results in both the simulated traffic environment and the HighD dataset demonstrate that our method can achieve multi-objective compatible autonomous driving in terms of driving efficiency, action consistency, and safety. It enhances the general performance of the driving while significantly increasing training efficiency.

Large language models (LLMs) are remarked by their substantial computational requirements. To mitigate the cost, researchers develop specialized CUDA kernels, which often fuse several tensor operations to maximize the utilization of GPUs as much as possible. However, those specialized kernels may still leave performance on the table as CUDA assembly experts show that manual optimization of GPU SASS schedules can lead to better performance, and trial-and-error is largely employed to manually find the best GPU SASS schedules. In this work, we employ an automatic approach to optimize GPU SASS schedules, which thus can be integrated into existing compiler frameworks. The key to automatic optimization is training an RL agent to mimic how human experts perform manual scheduling. To this end, we formulate an assembly game, where RL agents can play to find the best GPU SASS schedules. The assembly game starts from a \textit{-O3} optimized SASS schedule, and the RL agents can iteratively apply actions to mutate the current schedules. Positive rewards are generated if the mutated schedules get higher throughput by executing on GPUs. Experiments show that CuAsmRL can further improve the performance of existing specialized CUDA kernels transparently by up to $26\%$, and on average $9\%$. Moreover, it is used as a tool to reveal potential optimization moves learned automatically.

The effective design of patrol strategies is a difficult and complex problem, especially in medium and large areas. The objective is to plan, in a coordinated manner, the optimal routes for a set of patrols in a given area, in order to achieve maximum coverage of the area, while also trying to minimize the number of patrols. In this paper, we propose a multi-agent reinforcement learning (MARL) model, based on a decentralized partially observable Markov decision process, to plan unpredictable patrol routes within an urban environment represented as an undirected graph. The model attempts to maximize a target function that characterizes the environment within a given time frame. Our model has been tested to optimize police patrol routes in three medium-sized districts of the city of Malaga. The aim was to maximize surveillance coverage of the most crime-prone areas, based on actual crime data in the city. To address this problem, several MARL algorithms have been studied, and among these the Value Decomposition Proximal Policy Optimization (VDPPO) algorithm exhibited the best performance. We also introduce a novel metric, the coverage index, for the evaluation of the coverage performance of the routes generated by our model. This metric is inspired by the predictive accuracy index (PAI), which is commonly used in criminology to detect hotspots. Using this metric, we have evaluated the model under various scenarios in which the number of agents (or patrols), their starting positions, and the level of information they can observe in the environment have been modified. Results show that the coordinated routes generated by our model achieve a coverage of more than $90\%$ of the $3\%$ of graph nodes with the highest crime incidence, and $65\%$ for $20\%$ of these nodes; $3\%$ and $20\%$ represent the coverage standards for police resource allocation.

We provide an original theoretical study of Inverse Reinforcement Learning (IRL) through the lens of reward compatibility, a novel framework to quantify the compatibility of a reward with the given expert's demonstrations. Intuitively, a reward is more compatible with the demonstrations the closer the performance of the expert's policy computed with that reward is to the optimal performance for that reward. This generalizes the notion of feasible reward set, the most common framework in the theoretical IRL literature, for which a reward is either compatible or not compatible. The grayscale introduced by the reward compatibility is the key to extend the realm of provably efficient IRL far beyond what is attainable with the feasible reward set: from tabular to large-scale MDPs. We analyze the IRL problem across various settings, including optimal and suboptimal expert's demonstrations and both online and offline data collection. For all of these dimensions, we provide a tractable algorithm and corresponding sample complexity analysis, as well as various insights on reward compatibility and how the framework can pave the way to yet more general problem settings.

Robotic systems are increasingly employed for industrial automation, with contact-rich tasks like polishing requiring dexterity and compliant behaviour. These tasks are difficult to model, making classical control challenging. Deep reinforcement learning (RL) offers a promising solution by enabling the learning of models and control policies directly from data. However, its application to real-world problems is limited by data inefficiency and unsafe exploration. Adaptive hybrid RL methods blend classical control and RL adaptively, combining the strengths of both: structure from control and learning from RL. This has led to improvements in data efficiency and exploration safety. However, their potential for hardware applications remains underexplored, with no evaluations on physical systems to date. Such evaluations are critical to fully assess the practicality and effectiveness of these methods in real-world settings. This work presents an experimental demonstration of the hybrid RL algorithm CHEQ for robotic polishing with variable impedance, a task requiring precise force and velocity tracking. In simulation, we show that variable impedance enhances polishing performance. We compare standalone RL with adaptive hybrid RL, demonstrating that CHEQ achieves effective learning while adhering to safety constraints. On hardware, CHEQ achieves effective polishing behaviour, requiring only eight hours of training and incurring just five failures. These results highlight the potential of adaptive hybrid RL for real-world, contact-rich tasks trained directly on hardware.

Model-based offline reinforcement learning approaches generally rely on bounds of model error. Estimating these bounds is usually achieved through uncertainty estimation methods. In this work, we combine parametric and nonparametric methods for uncertainty estimation through a novel latent space based metric. In particular, we build upon recent advances in Riemannian geometry of generative models to construct a pullback metric of an encoder-decoder based forward model. Our proposed metric measures both the quality of out-of-distribution samples as well as the discrepancy of examples in the data.

Finding approximate Nash equilibria in zero-sum imperfect-information games is challenging when the number of information states is large. Policy Space Response Oracles (PSRO) is a deep reinforcement learning algorithm grounded in game theory that is guaranteed to converge to an approximate Nash equilibrium. However, PSRO requires training a reinforcement learning policy at each iteration, making it too slow for large games. We show through counterexamples and experiments that DCH and Rectified PSRO, two existing approaches to scaling up PSRO, fail to converge even in small games. We introduce Pipeline PSRO (P2SRO), the first scalable PSRO-based method for finding approximate Nash equilibria in large zero-sum imperfect-information games.

Deep reinforcement learning has generated superhuman AI in competitive games such as Go and StarCraft. Can similar learning techniques create a superior AI teammate for human-machine collaborative games? Will humans prefer AI teammates that improve objective team performance or those that improve subjective metrics of trust? In this study, we perform a single-blind evaluation of teams of humans and AI agents in the cooperative card game Hanabi, with both rule-based and learning-based agents. In addition to the game score, used as an objective metric of the human-AI team performance, we also quantify subjective measures of the human's perceived performance, teamwork, interpretability, trust, and overall preference of AI teammate.

Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry. This task is of great importance for predicting structure-activity relationships for a wide variety of substances ranging from biomolecules to ubiquitous materials. Substantial computational resources are invested in Monte Carlo and Molecular Dynamics methods to generate diverse and representative conformer sets for medium to large molecules, which are yet intractable to chemoinformatic conformer search methods. We present TorsionNet, an efficient sequential conformer search technique based on reinforcement learning under the rigid rotor approximation. The model is trained via curriculum learning, whose theoretical benefit is explored in detail, to maximize a novel metric grounded in thermodynamics called the Gibbs Score.