Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning

Identification of Failure Modes in the Collision Avoidance System of an Autonomous Ferry using Adaptive Stress Testing

Reinforcement learning (RL) has garnered significant attention for developing decision-making agents that aim to maximize rewards, specified by an external supervisor, within fully observable environments. However, many real-world problems involve partial or noisy observations, where agents cannot access complete and accurate information about the environment. These problems are commonly formulated as partially observable Markov decision processes (POMDPs). Previous studies have tackled RL in POMDPs by either incorporating the memory of past actions and observations or by inferring the true state of the environment from observed data. Nevertheless, aggregating observations and actions over time becomes impractical in problems with large decision-making time horizons and high-dimensional spaces. Furthermore, inference-based RL approaches often require many environmental samples to perform well, as they focus solely on reward maximization and neglect uncertainty in the inferred state. Active inference (AIF) is a framework naturally formulated in POMDPs and directs agents to select actions by minimizing a function called expected free energy (EFE). This supplies reward-maximizing (or exploitative) behavior, as in RL, with information-seeking (or exploratory) behavior. Despite this exploratory behavior of AIF, its use is limited to problems with small time horizons and discrete spaces due to the computational challenges associated with EFE. In this article, we propose a unified principle that establishes a theoretical connection between AIF and RL, enabling seamless integration of these two approaches and overcoming their limitations in continuous space POMDP settings. We substantiate our findings with rigorous theoretical analysis, providing novel perspectives for using AIF in designing and implementing artificial agents. Experimental results demonstrate the superior learning capabilities of our method compared to other alternative RL approaches in solving partially observable tasks with continuous spaces. Notably, our approach harnesses information-seeking exploration, enabling it to effectively solve reward-free problems and rendering explicit task reward design by an external supervisor optional.

We analyze data from simulated aircraft encounters to validate and inform the development of a prototype aircraft collision avoidance system. The high-dimensional and heterogeneous time series dataset is analyzed to discover properties of near mid-air collisions (NMACs) and categorize the NMAC encounters. Domain experts use these properties to better organize and understand NMAC occurrences. Existing solutions either are not capable of handling high-dimensional and heterogeneous time series datasets or do not provide explanations that are interpretable by a domain expert. The latter is critical to the acceptance and deployment of safety-critical systems. To address this gap, we propose grammar-based decision trees along with a learning algorithm. Our approach extends decision trees with a grammar framework for classifying heterogeneous time series data. A context-free grammar is used to derive decision expressions that are interpretable, application-specific, and support heterogeneous data types. In addition to classification, we show how grammar-based decision trees can also be used for categorization, which is a combination of clustering and generating interpretable explanations for each cluster. We apply grammar-based decision trees to a simulated aircraft encounter dataset and evaluate the performance of four variants of our learning algorithm. The best algorithm is used to analyze and categorize near mid-air collisions in the aircraft encounter dataset. We describe each discovered category in detail and discuss its relevance to aircraft collision avoidance.

Generalizability is a formidable challenge in applying reinforcement learning to the real world. The root cause of poor generalization performance in reinforcement learning is that generalization from a limited number of training conditions to unseen test conditions results in implicit partial observability, effectively transforming even fully observed Markov Decision Process (MDP) into Partially Observable Markov Decision Process (POMDP). To address such issues, we propose a novel structure, namely Context-adapted Multi-policy Ensemble Method (CAMPE), which enables the model to adapt to changes in the environment and efficiently solve implicit partial observability during generalization. The method captures local dynamic changes by learning contextual environment latent variables to equip the model with the ability of environment adaption. The latent variables and samples with contextual information are used as the input of the policy. Multiple policies are trained, combined in an integrated way to obtain a single policy to approximately solve the problem of partial observability. We demonstrate our method on various simulated robotics and control tasks. Experimental results show that our method achieves superior generalization ability.

Reinforcement learning (RL) offers a powerful paradigm for adaptive motion planning in complex driving environments. However, applying RL to autonomous driving remains challenging due to uncertainty from partial observability and the stochastic, multimodal behaviors of traffic participants. This paper presents a novel risk-aware RL framework for non-conservative motion planning under uncertainty. By integrating Partially Observable Markov Decision Processes (POMDP) with a deep RL-based policy optimization scheme, the proposed approach explicitly models aleatoric uncertainty via a Gaussian Mixture Bayesian Belief Updater and a time-varying risk field. Additionally, an Adaptive Context-aware Attention (ACA) module is employed to prioritize critical targets for enhanced interaction modeling dynamically. Extensive experiments on the CARLA simulator show that the framework generalizes well across diverse traffic conditions, improving average reward by 65.74% and 64.02% in low-speed dense and high-speed sparse scenarios. It remains robust in challenging situations such as overtaking and sudden lane changes in the PeMS dataset. Furthermore, distributed deployment tests confirm a real-time performance of 10 Hz on a hardware-in-the-loop platform, demonstrating the feasibility of practical deployment.

Load balancing arises as a fundamental problem, underlying the dimensioning and operation of many computing and communication systems, such as job routing in data center clusters, multipath communication, Big Data and queueing systems. In essence, the decision-making agent maps each arriving job to one of the possibly heterogeneous servers while aiming at an optimization goal such as load balancing, low average delay or low loss rate. One main difficulty in finding optimal load balancing policies here is that the agent only partially observes the impact of its decisions, e.g., through the delayed acknowledgements of the served jobs. In this paper, we provide a partially observable (PO) model that captures the load balancing decisions in parallel buffered systems under limited information of delayed acknowledgements. We present a simulation model for this PO system to find a load balancing policy in real-time using a scalable Monte Carlo tree search algorithm. We numerically show that the resulting policy outperforms other limited information load balancing strategies such as variants of Join-the-Most-Observations and has comparable performance to full information strategies like: Join-the-Shortest-Queue, Join-the-Shortest-Queue(d) and Shortest-Expected-Delay. Finally, we show that our approach can optimise the real-time parallel processing by using network data provided by Kaggle.

Tree search algorithms are widely applied methods to model and solve sequential decision problems. In particular, the family of sampling-based tree search algorithms called Monte Carlo Tree Search (MCTS) has had great success in problems with large branching factors. However, Real-Time Strategy (RTS) games offer a challenging testbed for tree search algorithms due to their large combinatorial action spaces, partial observability, simultaneous moves, and other factors, making them beyond the grasp of even current MCTS algorithms. This thesis makes contributions towards scaling MCTS algorithms to become more effective and efficient in the domain of RTS games. Specifically, this thesis contributes on the following problems. Firstly, we explore the problem of the integration of MCTS and domain knowledge, in the form of unit-action probability distributions, state evaluation functions, and scripted bots. Secondly, we investigate the optimization of gameplay/rollout policies for MCTS. Third, we study methods for self-learning in MCTS, where tree and/or rollout policies are bootstrapped directly from MCTS behavior iteratively.

The rapid global deployment of fifth-generation (5G) mobile networks has introduced unprecedented operational complexity within the 5G core, driven by cloud-native architectures, network function virtualization, software-defined networking, and ultra-low latency service requirements. Ensuring sustained high availability for 5G core networks serving millions of subscribers therefore demands a systematic operational reliability engineering approach that goes beyond traditional fault management and redundancy models. This paper proposes an Operational Reliability Engineering Framework designed to support continuous service availability, resilience, and performance stability in large-scale 5G core environments. The framework integrates reliability engineering principles with real-time observability, predictive analytics, automated fault isolation, and lifecycle-driven resilience planning across both physical and virtual network functions. Key framework components include reliability-centered design, proactive failure mode and effects analysis, service-based architecture dependency mapping, intelligent incident response orchestration, and closed-loop feedback mechanisms for continuous improvement. The proposed framework emphasizes the operationalization of reliability through measurable indicators such as service availability, mean time to detect, mean time to recover, and customer-impact metrics, aligned with strict service level agreements. A layered reliability governance model is introduced to coordinate network operations, DevOps, and vendor ecosystems, ensuring consistent reliability assurance across distributed cloud infrastructures. The framework also addresses scalability challenges, dynamic traffic behavior, and evolving threat landscapes by embedding adaptive capacity planning, stress testing, and fault-injection techniques into routine operations. By providing a structured and actionable reliability model tailored to 5G core networks, this study contributes a practical blueprint for telecom operators seeking to achieve sustained high availability at national and global scale. The framework supports not only technical robustness but also operational decision-making, enabling operators to proactively manage risk, reduce unplanned outages, and maintain service continuity in highly dynamic 5G environments. Overall, the proposed Operational Reliability Engineering Framework offers a comprehensive and scalable approach to sustaining high availability in mission-critical 5G core networks serving millions of users. The framework is intended to be technology-agnostic, interoperable with multivendor ecosystems, and applicable across standalone and non-standalone 5G deployments, supporting long-term network evolution while preserving operational stability, regulatory compliance, service assurance objectives, and continuous alignment with emerging industry standards and best practices worldwide today globally.

Introduction Reinforcement learning formalizes the concept of learning from interactions.1 Broadly, reinforcement learning focuses on a setting in which an agent (decision maker) sequentially interacts with an environment that is partially unknown to them. At each stage, the agent takes an action and receives a reward. The objective of the agent is to maximize rewards accumulated in the long run. There are many situations in health care where decisions are made sequentially for which reinforcement learning approaches could prove useful for decision making. Throughout this article, we consider treatment prescription as an archetypical example to connect reinforcement learning concepts to a health care setting. In this setting, the care provider, the prescribed treatment, and the patients can be viewed as the agent, the action, and the environment, respectively, as depicted in Figure 1.Figure 1: Sequential treatment of AKI or CKD complications modeled as a reinforcement learning problem.Background In this section, with the objective of making reinforcement learning literature more accessible to a clinical audience, we briefly introduce related fundamental concepts and approaches. We refer the interested reader to Sutton and Barto1 for a comprehensive introduction to reinforcement learning. Markov Decision Processes Markov decision processes (MDPs) are a formalism of the sequential decision-making problem that has been central to the theoretical and practical advancements of reinforcement learning. In each stage of an MDP, the agent observes the state of the environment and takes an action, which, in turn, results in a change of the state. This change of state is assumed to be probabilistic with the next state being determined only by the preceding state, the chosen action, and the transition probability. The agent also receives a reward that is a function of the taken action, the preceding state, and the subsequent state. In an MDP, the objective of the agent is to maximize the return defined as the reward accumulated over a time horizon. In some applications, it is common to consider the horizon to be infinite, in which case the future rewards are discounted by a factor smaller than one. The selection of action by the agent on the basis of the observed state is known as the policy. More formally, a policy is a probabilistic mapping from states to each possible action. Because the policy and the reward are a function of the state, it is critical to estimate the utility of being in a certain state. More specifically, the value function is defined as the expected return starting from a given state under the chosen policy. Under this formalism, the objective of the agent is to find the optimal policy that maximizes the value function for all states. Reinforcement Learning Methods Action-value methods are a class of reinforcement learning methods in which the actions are chosen on the basis of the estimation of their long-term value. A prominent example of an action-value method is Q-learning in which the agent iteratively takes actions with the highest estimated values and updates the action-state value function on the basis of new observations. Policy gradient methods are another class of reinforcement learning methods that seek to optimize the policy directly instead of choosing actions on the basis of their respective estimated value. Such methods could be advantageous in health care applications that entail a large number of possible actions, e.g., when recommending a wide range of drug dosages or treatment options. Clinical Applications Reinforcement learning frameworks and methods are broadly applicable to clinical settings in which decisions are made sequentially. A prominent clinical application of reinforcement learning is for treatment recommendation, which has been studied across a variety of diseases and treatments including radiation and chemotherapy for cancer, brain stimulation for epilepsy, and treatment strategies for sepsis.2–5 In such treatment recommendation settings, a policy is commonly known as a dynamic treatment regime. There are various other clinical applications of reinforcement learning including diagnosis, medical imaging, and decision support tools (see refs. 2–5 and the references therein). Reinforcement Learning in Nephrology Although there have been recent applications of machine learning in nephrology,6,7 to the best of the authors' knowledge, the application of reinforcement learning to nephrology has been primarily limited to optimizing the erythropoietin dosage in hemodialysis patients.8,9 However, there are other settings where reinforcement learning has the potential to improve patient care in nephrology. For example, reinforcement learning methods can be adopted in the treatment of the complications of AKI or CKD (Figure 1). In this problem, the state models the conditions of the patient (e.g., vital signs, laboratory test results including urine and blood tests, and urine output measurements). The action refers to the treatment options (e.g., the dosage of medications such as sodium polystyrene sulfonate, and hemodialysis). The reward models the improvement in patient conditions. Similarly, reinforcement learning can help automate and optimize the dosage of immunosuppressive drugs in kidney transplants. Challenges and Opportunities Despite the success of reinforcement learning in several simplified clinical settings, their large-scale application to patient care faces several open challenges. The complexity of human biology complicates modeling clinical decision making as a reinforcement learning problem. The state space in such settings is often enormous, which could make a purely computational approach infeasible. Moreover, modeling all potential objectives a priori as a reward function may not be feasible. To overcome these challenges and realize the potential of reinforcement learning, clinical insight can play a pivotal role. More specifically, restricting the state space to only include highly relevant clinical variables could greatly reduce the computational complexity. Furthermore, using inverse reinforcement learning,2 relevant reward functions can be learned from retrospective studies assuming the optimality of clinical decisions. Another critical challenge is addressing moral and ethical concerns. It is imperative to ensure that reinforcement learning methods do not cause harm to the patient. To this end, there exists a need for a thorough validation of such methods before their use in patient care. Hence, there is a need to go beyond retrospective studies that have been used for the proof of concept of most existing reinforcement learning methods in health care applications.2,3 The lessons learned from the success of reinforcement learning in other application areas (e.g., self-driving cars) can help navigate the path to realizing its potential in health care. Accessible open-source simulation environments that enable researchers to compare various approaches are essential to the field of reinforcement learning. OpenAI Gym is currently the leading toolkit containing a wide range of simulated environments, e.g., surgical robotics.10 The development of high-quality and reliable simulation environments for nephrology and other health care applications can facilitate the development and validation of reinforcement learning methods beyond limited retrospective studies. The adoption of methods validated in such simulation environments in actual clinical settings will require clinicians' oversight. Similar to how self-driving cars require a human driver to ensure collision avoidance, clinicians' oversight is critical to ensure the safety of the patients, especially in the early stages of the adoption of reinforcement learning methods. The data from clinicians' decisions (e.g., overruling the automated treatment recommendation) can be used to improve the reliability of autonomous systems over time and reduce the burden of clinicians' oversight.

Current beam orientation optimization algorithms for radiotherapy, such as column generation (CG), are typically heuristic or greedy in nature because of the size of the combinatorial problem, which leads to suboptimal solutions. We propose a reinforcement learning strategy using a Monte Carlo Tree Search (MCTS) that can find a better beam orientation set in less time than CG. We utilize a reinforcement learning structure involving a supervised learning network to guide the MCTS and to explore the decision space of beam orientation selection problems. We previously trained a deep neural network (DNN) that takes in the patient anatomy, organ weights, and current beams, then approximates beam fitness values to indicate the next best beam to add. Here, we use this DNN to probabilistically guide the traversal of the branches of the Monte Carlo decision tree to add a new beam to the plan. To assess the feasibility of the algorithm, we used a test set of 13 prostate cancer patients, distinct from the 57 patients originally used to train and validate the DNN, to solve five-beam plans. To show the strength of the guided MCTS (GTS) compared to other search methods, we also provided the performances of Guided Search, Uniform Tree Search and Random Search algorithms. On average, GTS outperformed all the other methods. It found a better solution than CG in 237 s on average, compared to 360 s for CG, and outperformed all other methods in finding a solution with a lower objective function value in less than 1000 s. Using our GTS method, we could maintain planning target volume (PTV) coverage within 1% error similar to CG, while reducing the organ-at-risk mean dose for body, rectum, left and right femoral heads; the mean dose to bladder was 1% higher with GTS than with CG.

In computer science, reinforcement learning is a powerful framework with which artificial agents can learn to maximize their performance for any given Markov decision process (MDP). Advances over the last decade, in combination with deep neural networks, have enjoyed performance advantages over humans in many difficult task settings. However, such frameworks perform far less favorably when evaluated in their ability to generalize or transfer representations across different tasks. Existing algorithms that facilitate transfer typically are limited to cases in which the transition function or the optimal policy is portable to new contexts, but achieving “deep transfer” characteristic of human behavior has been elusive. Such transfer typically requires discovery of abstractions that permit analogical reuse of previously learned representations to superficially distinct tasks. Here, we demonstrate that abstractions that minimize error in predictions of reward outcomes generalize across tasks with different transition and reward functions. Such reward-predictive representations compress the state space of a task into a lower dimensional representation by combining states that are equivalent in terms of both the transition and reward functions. Because only state equivalences are considered, the resulting state representation is not tied to the transition and reward functions themselves and thus generalizes across tasks with different reward and transition functions. These results contrast with those using abstractions that myopically maximize reward in any given MDP and motivate further experiments in humans and animals to investigate if neural and cognitive systems involved in state representation perform abstractions that facilitate such equivalence relations.

Reinforcement Learning (RL) Markov Decision Processes is studied with an emphasis on the well-studied exploration problem. We first formulate and discuss a definition of “efficient” algorithms that is termed Probably Approximately Correct (PAC) in RL. Next we provide general sufficient conditions for such an algorithm that applies to several different modeling assumptions. The conditions can be used to demonstrate that efficient learning is possible in finite MDPs, with either a model-based or model-free approach, in factored MDPs, and in continuous MDPs with linear dynamics. In the reinforcement-learning (RL) problem (Sutton & Barto 1998), an agent acts in an unknown or incompletely known environment with the goal of maximizing an external reward signal. In the most standard mathematical formulation of the problem, the environment is modeled as a Markov Decision Process (MDP) and the goal of the agent is to obtain near-optimal discounted return. Over the years, many algorithms have been proposed for this problem, but analyses of their performances have been relatively scarce. In fact, until recently, most theoretical guarantees have been that certain algorithms will discover an optimal policy in the limit, after an infinite amount of experience. In contrast, several attempts have been made to study “Probably Approximately Correct” or PAC-MDP algorithms, which exhibit near-optimal behavior in polynomial time and experience. This paper discusses several extensions of those results. We present a theorem that provides sufficient conditions for an algorithm to be PAC-MDP. We examine these conditions and show how they can be applied to prove that efficient learning is possible in three interesting scenerios: finite MDPs (i.e. the “Tabular case”),

This paper addresses a control problem for probabilistic models in the setting of Markov decision processes (MDP). We are interested in the steady-state control problem which asks, given an ergodic MDP $\mathcal{M}$ and a distribution δ goal, whether there exists a (history-dependent randomized) policy π ensuring that the steady-state distribution of $\mathcal{M}$ under π is exactly δ goal. We first show that stationary randomized policies suffice to achieve a given steady-state distribution. Then we infer that the steady-state control problem is decidable for MDP, and can be represented as a linear program which is solvable in PTIME. This decidability result extends to labeled MDP (LMDP) where the objective is a steady-state distribution on labels carried by the states, and we provide a PSPACE algorithm. We also show that a related steady-state language inclusion problem is decidable in EXPTIME for LMDP. Finally, we prove that if we consider MDP under partial observation (POMDP), the steady-state control problem becomes undecidable.

An Attributed Dynamic Graph (ADG) contains multiple dynamic attributes associated with each edge in the graph, where people usually can specify multiple constraints in the attributes to illustrate their requirements, such as the total cost, the total travel time and the stopover interval of a flight between two cities. This inspires the Multi-Constrained Temporal Path (MCTP) discovery in ADGs, which is a challenging NP-Complete problem. The existing methods adopt Reinforcement Learning (RL) and Monte Carlo Tree Search (MCTS) in MCTP discovery. However, they require a certain degree of discovery experience to obtain better results, which can lead to the expensive cost of query time and storage space, and thus are not applicable in real-time applications. This motivates us to develop a new Adaptive Monte Carlo Tree Search algorithm (A-MCTS). A-MCTS dynamically adjusts the priority of historical records that are used in MCTS to improve the performance and reduce the size of required discovery experience. The experimental results on ten real-world dynamic graphs demonstrate that our proposed A-MCTS outperforms the state-of-the-art methods in terms of both efficiency and effectiveness. IEEE

Reinforcement Learning (RL) is a machine learning methodology that develops the capability to make sequential decisions in intricate issues using trial-and-error techniques. RL has become increasingly prevalent for decision-making and control tasks in diverse fields such as industrial processes, biochemical systems and energy management. This review paper presents a comprehensive examination of the development, models, algorithms and practical uses of RL, with a specific emphasis on its application in process control. The study examines the fundamental theories, methodology and applications of RL, classifying them into two categories: classical RL such as such as Markov decision processes (MDP) and deep RL viz., actor critic methods. RL is a topic of discussion in multiple process industries, such as industrial chemical process control, biochemical process control, energy systems, wastewater treatment and the oil and gas sector. Nevertheless, the paper also highlights challenges that hinder its larger acceptance, including the requirement for substantial computational resources, the complexity of simulating real-world settings and the challenge of guaranteeing the stability and resilience of RL algorithms in dynamic and unpredictable environments. RL has demonstrated significant promise, but more research is needed to fully integrate it into industrial and environmental systems in order to solve the current challenges. Abbreviations: AC: Actor critic; AI: Artificial intelligence; ANN: Artificial neural networks; A3C: Asynchronous advantage actor critic; CRL : Classical Reinforcement learning; CV : Controlled variable; DDPG : Deep deterministic policy gradient; DQN: Deep Q network; DRL: Deep reinforcement learning; DP: Dynamic programming; FOMDP: Fully observable Markov decision process; GRU: Gated recurrent unit; LQR: Linear quadratic regulator; LSTM: Long short-term memory; ML: Machine learning; MV : Manipulated variable; MC: Monte Carlo; MDP: Markov decision process; MPC: Model predictive controller; MIMO: Multi input multi output; PG: Policy gradient; PID: Proportional integral derivative; PPO: Proximal policy optimisation; RL: Reinforcement learning; PPO: Proximal policy optimisation; SAC: Soft actor critic; SISO: Single input single output; TD: Temporal difference; TRPO: Trust region policy optimisation; TD3: Twin delayed deep deterministic policy gradient.