arXiv subjects

Dominik Wojtczak

Publications and source records attributed to Dominik Wojtczak.

At least 19 recordsLinked to original sources

arXiv2026

Learning Multi-Timescale Interventions under Safety and Resource Constraints

Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce persistent effects that continue to shape future states long after the decision that initiated them. An agent must then decide jointly when to intervene, which temporal mode to use and how strongly, while accounting for residual effects and limited intervention resources. We introduce MINT: Multi-timescale Intervention Network Training. Persistent effects are carried by an augmented intervention state that accumulates and decays, while a structured policy separates intervention-mode selection from conditional control. Unlike temporal abstractions that extend policy execution, persistent-effect interventions remain part of the environment dynamics and may overlap with later interventions. We show that the augmented state is a sufficient statistic for the intervention history, preserving the Markov property, and establish Bellman contraction and almost-sure convergence of a tabular Q-learning instance. Across persistent-control MuJoCo locomotion, stochastic inventory management, and a physiologically grounded Type 1 Diabetes Mellitus (T1DM) simulator, MINT attains the best mean primary metric on two of three benchmarks while using fewer intervention activations than an identically augmented flat policy. Its return advantage is present at every binding intervention budget and narrows to parity in the unconstrained reference setting. In T1DM it achieves $90.9\pm0.9\%$ time in range with zero time below range, improving on the strongest baseline by $21.5\%$ points. Code, benchmarks and the configuration for every reported run are available at https://github.com/heywanrong/mint-rl.

cs.LG↗

arXiv2026

Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks

While Large Language Models demonstrate immense potential as proactive Medical Agents, their real-world deployment is severely bottlenecked by data scarcity under privacy constraints. To overcome this, we propose State-Enhanced Logical-Skill Memory (SELSM), a training-free framework that distills simulated clinical trajectories into entity-agnostic operational rules within an abstract skill space. During inference, a Query-Anchored Two-Stage Retrieval mechanism dynamically fetches these entity-agnostic logical priors to guide the agent's step-by-step reasoning, effectively resolving the state polysemy problem. Evaluated on MedAgentBench -- the only authoritative high-fidelity virtual EHR sandbox benchmarked with real clinical data -- SELSM substantially elevates the zero-shot capabilities of locally deployable foundation models (30B--32B parameters). Notably, on the Qwen3-30B-A3B backbone, our framework completely eliminates task chain breakdowns to achieve a 100\% completion rate, boosting the overall success rate by an absolute 22.67\% and significantly outperforming existing memory-augmented baselines. This study demonstrates that equipping models with a dynamically updatable, state-enhanced cognitive scaffold is a privacy-preserving and computationally efficient pathway for local adaptation of AI agents to clinical information systems. While currently validated on FHIR-based EHR interactions as an initial step, the entity-agnostic design of SELSM provides a principled foundation toward broader clinical deployment.

cs.AI↗

arXiv2026

A Survey for Deep Reinforcement Learning Based Network Intrusion Detection

Cyber-attacks are becoming increasingly sophisticated and frequent, highlighting the importance of network intrusion detection systems. This paper explores the potential and challenges of using deep reinforcement learning (DRL) in network intrusion detection. It begins by introducing key DRL concepts and frameworks, such as deep Q-networks and actor-critic algorithms, and reviews recent research utilizing DRL for intrusion detection. The study evaluates challenges related to model training efficiency, detection of minority and unknown class attacks, feature selection, and handling unbalanced datasets. The performance of DRL models is comprehensively analyzed, showing that while DRL holds promise, many recent technologies remain underexplored. Some DRL models achieve state-of-the-art results on public datasets, occasionally outperforming traditional deep learning methods. The paper concludes with recommendations for enhancing DRL deployment and testing in real-world network scenarios, with a focus on Internet of Things intrusion detection. It discusses recent DRL architectures and suggests future policy functions for DRL-based intrusion detection. Finally, the paper proposes integrating DRL with generative methods to further improve performance, addressing current gaps and supporting more robust and adaptive network intrusion detection systems.

cs.CR↗

arXiv2026

The Complexity of Games with Randomised Control

We study the complexity of solving two-player infinite duration games played on a fixed finite graph, where the control of a node is not predetermined but rather assigned randomly. In classic random-turn games, control of each node is assigned randomly every time the node is visited during a play. In this work, we study two natural variants of this where control of each node is assigned only once: (i) control is assigned randomly during a play when a node is visited for the first time and does not change for the rest of the play and (ii) control is assigned a priori before the game starts for every node by independent coin tosses and then the game is played. We investigate the complexity of computing the winning probability with three kinds of objectives-reachability, parity, and energy. We show that the qualitative questions on all variants and all objectives are NL-complete. For the quantitative questions, we show that deciding whether the maximiser can win with probability at least a given threshold for every objective is PSPACE-complete under the first mechanism, and that computing the exact winning probability for every objective is sharp-P-complete under the second. To complement our hardness results for the second mechanism, we propose randomised approximation schemes that efficiently estimate the winning probability for all three objectives, assuming a bounded number of parity colours and unary-encoded weights for energy objectives, and we empirically demonstrate their fast convergence.

cs.GT↗

arXiv2024

Dive into Machine Learning Algorithms for Influenza Virus Host Prediction with Hemagglutinin Sequences

Influenza viruses mutate rapidly and can pose a threat to public health, especially to those in vulnerable groups. Throughout history, influenza A viruses have caused pandemics between different species. It is important to identify the origin of a virus in order to prevent the spread of an outbreak. Recently, there has been increasing interest in using machine learning algorithms to provide fast and accurate predictions for viral sequences. In this study, real testing data sets and a variety of evaluation metrics were used to evaluate machine learning algorithms at different taxonomic levels. As hemagglutinin is the major protein in the immune response, only hemagglutinin sequences were used and represented by position-specific scoring matrix and word embedding. The results suggest that the 5-grams-transformer neural network is the most effective algorithm for predicting viral sequence origins, with approximately 99.54% AUCPR, 98.01% F1 score and 96.60% MCC at a higher classification level, and approximately 94.74% AUCPR, 87.41% F1 score and 80.79% MCC at a lower classification level.

cs.LG↗

arXiv2024

MC-NN: An End-to-End Multi-Channel Neural Network Approach for Predicting Influenza A Virus Hosts and Antigenic Types

Influenza poses a significant threat to public health, particularly among the elderly, young children, and people with underlying dis-eases. The manifestation of severe conditions, such as pneumonia, highlights the importance of preventing the spread of influenza. An accurate and cost-effective prediction of the host and antigenic sub-types of influenza A viruses is essential to addressing this issue, particularly in resource-constrained regions. In this study, we propose a multi-channel neural network model to predict the host and antigenic subtypes of influenza A viruses from hemagglutinin and neuraminidase protein sequences. Our model was trained on a comprehensive data set of complete protein sequences and evaluated on various test data sets of complete and incomplete sequences. The results demonstrate the potential and practicality of using multi-channel neural networks in predicting the host and antigenic subtypes of influenza A viruses from both full and partial protein sequences.

cs.LG↗

arXiv2023

Omega-Regular Decision Processes

Regular decision processes (RDPs) are a subclass of non-Markovian decision processes where the transition and reward functions are guarded by some regular property of the past (a lookback). While RDPs enable intuitive and succinct representation of non-Markovian decision processes, their expressive power coincides with finite-state Markov decision processes (MDPs). We introduce omega-regular decision processes (ODPs) where the non-Markovian aspect of the transition and reward functions are extended to an omega-regular lookahead over the system evolution. Semantically, these lookaheads can be considered as promises made by the decision maker or the learning agent about her future behavior. In particular, we assume that, if the promised lookaheads are not met, then the payoff to the decision maker is $\bot$ (least desirable payoff), overriding any rewards collected by the decision maker. We enable optimization and learning for ODPs under the discounted-reward objective by reducing them to lexicographic optimization and learning over finite MDPs. We present experimental results demonstrating the effectiveness of the proposed reduction.

cs.LO↗

arXiv2023

Predicting Influenza A Viral Host Using PSSM and Word Embeddings

The rapid mutation of the influenza virus threatens public health. Reassortment among viruses with different hosts can lead to a fatal pandemic. However, it is difficult to detect the original host of the virus during or after an outbreak as influenza viruses can circulate between different species. Therefore, early and rapid detection of the viral host would help reduce the further spread of the virus. We use various machine learning models with features derived from the position-specific scoring matrix (PSSM) and features learned from word embedding and word encoding to infer the origin host of viruses. The results show that the performance of the PSSM-based model reaches the MCC around 95%, and the F1 around 96%. The MCC obtained using the model with word embedding is around 96%, and the F1 is around 97%.

cs.CL↗

arXiv2023

Omega-Regular Reward Machines

Reinforcement learning (RL) is a powerful approach for training agents to perform tasks, but designing an appropriate reward mechanism is critical to its success. However, in many cases, the complexity of the learning objectives goes beyond the capabilities of the Markovian assumption, necessitating a more sophisticated reward mechanism. Reward machines and omega-regular languages are two formalisms used to express non-Markovian rewards for quantitative and qualitative objectives, respectively. This paper introduces omega-regular reward machines, which integrate reward machines with omega-regular languages to enable an expressive and effective reward mechanism for RL. We present a model-free RL algorithm to compute epsilon-optimal strategies against omega-egular reward machines and evaluate the effectiveness of the proposed algorithm through experiments.

cs.LG↗

arXiv2022

Multi-channel neural networks for predicting influenza A virus hosts and antigenic types

Influenza occurs every season and occasionally causes pandemics. Despite its low mortality rate, influenza is a major public health concern, as it can be complicated by severe diseases like pneumonia. A fast, accurate and low-cost method to predict the origin host and subtype of influenza viruses could help reduce virus transmission and benefit resource-poor areas. In this work, we propose multi-channel neural networks to predict antigenic types and hosts of influenza A viruses with hemagglutinin and neuraminidase protein sequences. An integrated data set containing complete protein sequences were used to produce a pre-trained model, and two other data sets were used for testing the model's performance. One test set contained complete protein sequences, and another test set contained incomplete protein sequences. The results suggest that multi-channel neural networks are applicable and promising for predicting influenza A virus hosts and antigenic subtypes with complete and partial protein sequences.

q-bio.QM↗

arXiv2022

Recursive Reinforcement Learning

Recursion is the fundamental paradigm to finitely describe potentially infinite objects. As state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about recursion, they must rely on the practitioner's ingenuity in designing a suitable "flat" representation of the environment. The resulting manual feature constructions and approximations are cumbersome and error-prone; their lack of transparency hampers scalability. To overcome these challenges, we develop RL algorithms capable of computing optimal policies in environments described as a collection of Markov decision processes (MDPs) that can recursively invoke one another. Each constituent MDP is characterized by several entry and exit points that correspond to input and output values of these invocations. These recursive MDPs (or RMDPs) are expressively equivalent to probabilistic pushdown systems (with call-stack playing the role of the pushdown stack), and can model probabilistic programs with recursive procedural calls. We introduce Recursive Q-learning -- a model-free RL algorithm for RMDPs -- and prove that it converges for finite, single-exit and deterministic multi-exit RMDPs under mild assumptions.

cs.LG↗

arXiv2022

Alternating Good-for-MDP Automata

When omega-regular objectives were first proposed in model-free reinforcement learning (RL) for controlling MDPs, deterministic Rabin automata were used in an attempt to provide a direct translation from their transitions to scalar values. While these translations failed, it has turned out that it is possible to repair them by using good-for-MDPs (GFM) Büchi automata instead. These are nondeterministic Büchi automata with a restricted type of nondeterminism, albeit not as restricted as in good-for-games automata. Indeed, deterministic Rabin automata have a pretty straightforward translation to such GFM automata, which is bi-linear in the number of states and pairs. Interestingly, the same cannot be said for deterministic Streett automata: a translation to nondeterministic Rabin or Büchi automata comes at an exponential cost, even without requiring the target automaton to be good-for-MDPs. Do we have to pay more than that to obtain a good-for-MDP automaton? The surprising answer is that we have to pay significantly less when we instead expand the good-for-MDP property to alternating automata: like the nondeterministic GFM automata obtained from deterministic Rabin automata, the alternating good-for-MDP automata we produce from deterministic Streett automata are bi-linear in the the size of the deterministic automaton and its index, and can therefore be exponentially more succinct than minimal nondeterministic Büchi automata.

cs.FL↗

arXiv2022

A Recursive Approach to Solving Parity Games in Quasipolynomial Time

Zielonka's classic recursive algorithm for solving parity games is perhaps the simplest among the many existing parity game algorithms. However, its complexity is exponential, while currently the state-of-the-art algorithms have quasipolynomial complexity. Here, we present a modification of Zielonka's classic algorithm that brings its complexity down to $n^{O\left(\log\left(1+\frac{d}{\log n}\right)\right)}$, for parity games of size $n$ with $d$ priorities, in line with previous quasipolynomial-time solutions.

cs.GT↗

arXiv2021

Priority Promotion with Parysian Flair

We develop an algorithm that combines the advantages of priority promotion - one of the leading approaches to solving large parity games in practice - with the quasi-polynomial time guarantees offered by Parys' algorithm. Hybridising these algorithms sounds both natural and difficult, as they both generalise the classic recursive algorithm in different ways that appear to be irreconcilable: while the promotion transcends the call structure, the guarantees change on each level. We show that an interface that respects both is not only effective, but also efficient.

cs.DS↗

arXiv2021

Mungojerrie: Reinforcement Learning of Linear-Time Objectives

Reinforcement learning synthesizes controllers without prior knowledge of the system. At each timestep, a reward is given. The controllers optimize the discounted sum of these rewards. Applying this class of algorithms requires designing a reward scheme, which is typically done manually. The designer must ensure that their intent is accurately captured. This may not be trivial, and is prone to error. An alternative to this manual programming, akin to programming directly in assembly, is to specify the objective in a formal language and have it "compiled" to a reward scheme. Mungojerrie (https://plv.colorado.edu/mungojerrie/) is a tool for testing reward schemes for $ω$-regular objectives on finite models. The tool contains reinforcement learning algorithms and a probabilistic model checker. Mungojerrie supports models specified in PRISM and $ω$-automata specified in HOA.

cs.LG↗

arXiv2021

Model-free Reinforcement Learning for Branching Markov Decision Processes

We study reinforcement learning for the optimal control of Branching Markov Decision Processes (BMDPs), a natural extension of (multitype) Branching Markov Chains (BMCs). The state of a (discrete-time) BMCs is a collection of entities of various types that, while spawning other entities, generate a payoff. In comparison with BMCs, where the evolution of a each entity of the same type follows the same probabilistic pattern, BMDPs allow an external controller to pick from a range of options. This permits us to study the best/worst behaviour of the system. We generalise model-free reinforcement learning techniques to compute an optimal control strategy of an unknown BMDP in the limit. We present results of an implementation that demonstrate the practicality of the approach.

cs.LG↗

arXiv2021

Facility Reallocation on the Line

We consider a multi-stage facility reallocation problems on the real line, where a facility is being moved between time stages based on the locations reported by $n$ agents. The aim of the reallocation algorithm is to minimise the social cost, i.e., the sum over the total distance between the facility and all agents at all stages, plus the cost incurred for moving the facility. We study this problem both in the offline setting and online setting. In the offline case the algorithm has full knowledge of the agent locations in all future stages, and in the online setting the algorithm does not know these future locations and must decide the location of the facility on a stage-per-stage basis. We derive the optimal algorithm in both cases. For the online setting we show that its competitive ratio is $(n+2)/(n+1)$. As neither of these algorithms turns out to yield a strategy-proof mechanism, we propose another strategy-proof mechanism which has a competitive ratio of $(n+3)/(n+1)$ for odd $n$ and $(n+4)/n$ for even $n$, which we conjecture to be the best possible. We also consider a generalisation with multiple facilities and weighted agents, for which we show that the optimum can be computed in polynomial time for a fixed number of facilities.

cs.GT↗

arXiv2021

Coordination Games on Weighted Directed Graphs

We study strategic games on weighted directed graphs, in which the payoff of a player is defined as the sum of the weights on the edges from players who chose the same strategy, augmented by a fixed non-negative integer bonus for picking a given strategy. These games capture the idea of coordination in the absence of globally common strategies. We identify natural classes of graphs for which finite improvement or coalition-improvement paths of polynomial length always exist, and, as a consequence, a (pure) Nash equlibrium or a strong equilibrium can be found in polynomial time. The considered classes of graphs are typical in network topologies: simple cycles correspond to the token ring local area networks, while open chains of simple cycles correspond to multiple independent rings topology from the recommendation G.8032v2 on the Ethernet ring protection switching. For simple cycles these results are optimal in the sense that without the imposed conditions on the weights and bonuses a Nash equilibrium may not even exist. Finally, we prove that the problem of determining the existence of a Nash equilibrium or of a strong equilibrium in these games is NP-complete already for unweighted graphs and with no bonuses assumed. This implies that the same problems for polymatrix games are strongly NP-hard.

cs.GT↗