arXiv subjects

Viliam Lisý

Publications and source records attributed to Viliam Lisý.

At least 19 recordsLinked to original sources

arXiv2026

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient algorithms and inherits their convergence guarantees towards Nash equilibria under an idealized model. Empirical evaluations across four benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of algorithms to posterior collapse in stochastic environments. We leave it as an open challenge.

cs.LG↗

arXiv2026

Towards Improving Sequential Decision-Making in LLM Agents via Experience Memory

Large language models have improved substantially on single-shot reasoning tasks, but their performance in sequential decision-making is less well understood. We study this on fully-observable two-player zero-sum games, which provide ground-truth evaluation: outcomes are determined by the rules, and optimality of individual moves can be computed or approximated, without relying on a judge model. Across model tiers, LLMs play suboptimally in simple games such as tic-tac-toe or Connect Four, and lose to MCTS opponents. Obfuscations that preserve the game tree but rewrite its surface form leave performance largely unchanged, indicating the gap is not fully explained by recall of memorized strategies. Motivated by this performance gap, we introduce an agentic framework enhanced with an experience memory designed for the sequential setting and addressing common challenges of sequential decision-making such as credit assignment. We show that post-game reflection and rule extraction yield measurable improvements on tic-tac-toe without modifying the model weights.

cs.AI↗

arXiv2026

Decoys Cannot Go Everywhere: Mapping the Deception Surface in MITRE ATT&CK

Cyber deception research often assumes that a decoy can be placed wherever there is attacker behavior. This work tests that assumption across MITRE ATT&CK v18.1. We introduce a four-criterion rubric for infrastructure deception and apply it to all 250 ATT&CK techniques. The rubric evaluates whether a defender-controlled decoy can be placed, whether an attacker is likely to interact with it, what intelligence that interaction can yield, and whether the interaction reliably indicates malice. The resulting deception surface is sparse: only 80 techniques (32%) admit a decoy the attacker could plausibly reach. For the remaining 170 techniques, there is no defender-controlled asset in the attacker's path that can be fabricated as a decoy. Decoy placement across those 80 techniques falls into two patterns we call Sweep and Seek. In Sweep, the attacker moves broadly through assets in range and encounters the decoy as part of that activity. In Seek, the attacker looks for a specific kind of asset and interacts with a fabricated version of it. These patterns give a simple placement rule: a decoy must either sit on a sweep path or imitate a sought asset. We also show that decoys usually have useful intelligence potential, but whether an attacker interacts with them at all, and whether that interaction reliably indicates malice, both vary. We release the rubric, decision rules, and per-technique assessment as an auditable baseline for future deception research and deployment planning, and show that infrastructure decoys cannot be assumed to apply to all attacker behavior.

cs.CR↗

arXiv2026

Superhuman AI for Generals.io Using Self-Play Reinforcement Learning

We present a superhuman AI agent for Generals.io, a real-time strategy game that requires both long-horizon planning and short-term tactics under strong imperfect information. Trained for four days on 4x NVIDIA H200 GPUs, our agent reaches #1 on the public 1v1 leaderboard of over 5,000 human players, leading the second-ranked player by the same margin that separates second place from 25th, and beats the two top-ranked humans head-to-head with a combined 199-70 record across 269 ladder matches. A key enabler is a JAX-native simulator that reaches tens of millions of frames per second on a single GPU, roughly a 10,000x speedup over the prior simulator. On top of this, we train a vision transformer policy end-to-end by self-play with a policy-gradient loop and sparse win/loss reward, using top-advantage sample filtering and an exponential moving average of the policy parameters. Taken together, our findings highlight what matters, and what does not, once a fast simulator removes the data bottleneck.

cs.LG↗

arXiv2025

Understanding Optimal Portfolios of Strategies for Solving Two-player Zero-sum Games

In large-scale games, approximating the opponent's strategy space with a small portfolio of representative strategies is a common and powerful technique. However, the construction of these portfolios often relies on domain-specific knowledge or heuristics with no theoretical guarantees. This paper establishes a formal foundation for portfolio-based strategy approximation. We define the problem of finding an optimal portfolio in two-player zero-sum games and prove that this optimization problem is NP-hard. We demonstrate that several intuitive heuristics-such as using the support of a Nash Equilibrium or building portfolios incrementally - can lead to highly suboptimal solutions. These negative results underscore the problem's difficulty and motivate the need for robust, empirically-validated heuristics. To this end, we introduce an analytical framework to bound portfolio quality and propose a methodology for evaluating heuristic approaches. Our evaluation of several heuristics shows that their success heavily depends on the specific game being solved. Our code is publicly available.

cs.GT↗

arXiv2025

Look-ahead Reasoning with a Learned Model in Imperfect Information Games

Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios. While MuZero enables effective model learning for search in perfect information games, extending this paradigm to imperfect information games presents substantial challenges due to more nuanced look-ahead reasoning techniques and large number of states relevant for individual decisions. This paper introduces an algorithm LAMIR that learns an abstracted model of an imperfect information game directly from the agent-environment interaction. During test time, this trained model is used to perform look-ahead reasoning. The learned abstraction limits the size of each subgame to a manageable size, making theoretically principled look-ahead reasoning tractable even in games where previous methods could not scale. We empirically demonstrate that with sufficient capacity, LAMIR learns the exact underlying game structure, and with limited capacity, it still learns a valuable abstraction, which improves game playing performance of the pre-trained agents even in large games.

cs.AI↗

arXiv2025

Adapting Beyond the Depth Limit: Counter Strategies in Large Imperfect Information Games

We study the problem of adapting to a known sub-rational opponent during online play while remaining robust to rational opponents. We focus on large imperfect-information (zero-sum) games, which makes it impossible to inspect the whole game tree at once and necessitates the use of depth-limited search. However, all existing methods assume rational play beyond the depth-limit, which only allows them to adapt a very limited portion of the opponent's behaviour. We propose an algorithm Adapting Beyond Depth-limit (ABD) that uses a strategy-portfolio approach - which we refer to as matrix-valued states - for depth-limited search. This allows the algorithm to fully utilise all information about the opponent model, making it the first robust-adaptation method to be able to do so in large imperfect-information games. As an additional benefit, the use of matrix-valued states makes the algorithm simpler than traditional methods based on optimal value functions. Our experimental results in poker and battleship show that ABD yields more than a twofold increase in utility when facing opponents who make mistakes beyond the depth limit and also delivers significant improvements in utility and safety against randomly generated opponents.

cs.GT↗

arXiv2024

Continual Depth-limited Responses for Computing Counter-strategies in Sequential Games

In zero-sum games, the optimal strategy is well-defined by the Nash equilibrium. However, it is overly conservative when playing against suboptimal opponents and it can not exploit their weaknesses. Limited look-ahead game solving in imperfect-information games allows defeating human experts in massive real-world games such as Poker, Liar's Dice, and Scotland Yard. However, since they approximate Nash equilibrium, they tend to only win slightly against weak opponents. We propose methods combining limited look-ahead solving with an opponent model in order to 1) approximate a best response in large games or 2) compute a robust response with control over the robustness of the response. Both methods can compute the response in real time to previously unseen strategies. We present theoretical guarantees of our methods. We show that existing robust response methods do not work combined with limited look-ahead solving of the shelf, and we propose a novel solution for the issue. Our algorithm performs significantly better than multiple baselines in smaller games and outperforms state-of-the-art methods against SlumBot.

cs.GT↗

arXiv2024

Classification with Costly Features in Hierarchical Deep Sets

Classification with Costly Features (CwCF) is a classification problem that includes the cost of features in the optimization criteria. Individually for each sample, its features are sequentially acquired to maximize accuracy while minimizing the acquired features' cost. However, existing approaches can only process data that can be expressed as vectors of fixed length. In real life, the data often possesses rich and complex structure, which can be more precisely described with formats such as XML or JSON. The data is hierarchical and often contains nested lists of objects. In this work, we extend an existing deep reinforcement learning-based algorithm with hierarchical deep sets and hierarchical softmax, so that it can directly process this data. The extended method has greater control over which features it can acquire and, in experiments with seven datasets, we show that this leads to superior performance. To showcase the real usage of the new method, we apply it to a real-life problem of classifying malicious web domains, using an online service.

cs.LG↗

arXiv2023

Revisiting Game Representations: The Hidden Costs of Efficiency in Sequential Decision-making Algorithms

Recent advancements in algorithms for sequential decision-making under imperfect information have shown remarkable success in large games such as limit- and no-limit poker. These algorithms traditionally formalize the games using the extensive-form game formalism, which, as we show, while theoretically sound, is memory-inefficient and computationally intensive in practice. To mitigate these challenges, a popular workaround involves using a specialized representation based on player specific information-state trees. However, as we show, this alternative significantly narrows the set of games that can be represented efficiently. In this study, we identify the set of large games on which modern algorithms have been benchmarked as being naturally represented by Sequential Bayesian Games. We elucidate the critical differences between extensive-form game and sequential Bayesian game representations, both theoretically and empirically. We further argue that the impressive experimental results often cited in the literature may be skewed, as they frequently stem from testing these algorithms only on this restricted class of games. By understanding these nuances, we aim to guide future research in developing more universally applicable and efficient algorithms for sequential decision-making under imperfect information.

cs.GT↗

arXiv2023

Generation of Games for Opponent Model Differentiation

Protecting against adversarial attacks is a common multiagent problem. Attackers in the real world are predominantly human actors, and the protection methods often incorporate opponent models to improve the performance when facing humans. Previous results show that modeling human behavior can significantly improve the performance of the algorithms. However, modeling humans correctly is a complex problem, and the models are often simplified and assume humans make mistakes according to some distribution or train parameters for the whole population from which they sample. In this work, we use data gathered by psychologists who identified personality types that increase the likelihood of performing malicious acts. However, in the previous work, the tests on a handmade game could not show strategic differences between the models. We created a novel model that links its parameters to psychological traits. We optimized over parametrized games and created games in which the differences are profound. Our work can help with automatic game generation when we need a game in which some models will behave differently and to identify situations in which the models do not align.

cs.AI↗

arXiv2023

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks and Autoregressive Policy Decomposition

We focus on reinforcement learning (RL) in relational problems that are naturally defined in terms of objects, their relations, and object-centric actions. These problems are characterized by variable state and action spaces, and finding a fixed-length representation, required by most existing RL methods, is difficult, if not impossible. We present a deep RL framework based on graph neural networks and auto-regressive policy decomposition that naturally works with these problems and is completely domain-independent. We demonstrate the framework's broad applicability in three distinct domains and show impressive zero-shot generalization over different problem sizes.

cs.LG↗

arXiv2023

NASimEmu: Network Attack Simulator & Emulator for Training Agents Generalizing to Novel Scenarios

Current frameworks for training offensive penetration testing agents with deep reinforcement learning struggle to produce agents that perform well in real-world scenarios, due to the reality gap in simulation-based frameworks and the lack of scalability in emulation-based frameworks. Additionally, existing frameworks often use an unrealistic metric that measures the agents' performance on the training data. NASimEmu, a new framework introduced in this paper, addresses these issues by providing both a simulator and an emulator with a shared interface. This approach allows agents to be trained in simulation and deployed in the emulator, thus verifying the realism of the used abstraction. Our framework promotes the development of general agents that can transfer to novel scenarios unseen during their training. For the simulation part, we adopt an existing simulator NASim and enhance its realism. The emulator is implemented with industry-level tools, such as Vagrant, VirtualBox, and Metasploit. Experiments demonstrate that a simulation-trained agent can be deployed in emulation, and we show how to use the framework to train a general agent that transfers into novel, structurally different scenarios. NASimEmu is available as open-source.

cs.CR↗

arXiv2022

Explaining Classifiers Trained on Raw Hierarchical Multiple-Instance Data

Learning from raw data input, thus limiting the need for feature engineering, is a component of many successful applications of machine learning methods in various domains. While many problems naturally translate into a vector representation directly usable in standard classifiers, a number of data sources have the natural form of structured data interchange formats (e.g., security logs in JSON/XML format). Existing methods, such as in Hierarchical Multiple Instance Learning (HMIL), allow learning from such data in their raw form. However, the explanation of the classifiers trained on raw structured data remains largely unexplored. By treating these models as sub-set selections problems, we demonstrate how interpretable explanations, with favourable properties, can be generated using computationally efficient algorithms. We compare to an explanation technique adopted from graph neural networks showing an order of magnitude speed-up and higher-quality explanations.

stat.ML↗

arXiv2022

Value Functions for Depth-Limited Solving in Zero-Sum Imperfect-Information Games

We provide a formal definition of depth-limited games together with an accessible and rigorous explanation of the underlying concepts, both of which were previously missing in imperfect-information games. The definition works for an arbitrary extensive-form game and is not tied to any specific game-solving algorithm. Moreover, this framework unifies and significantly extends three approaches to depth-limited solving that previously existed in extensive-form games and multiagent reinforcement learning but were not known to be compatible. A key ingredient of these depth-limited games are value functions. Focusing on two-player zero-sum imperfect-information games, we show how to obtain optimal value functions and prove that public information provides both necessary and sufficient context for computing them. We provide a domain-independent encoding of the domains that allows for approximating value functions even by simple feed-forward neural networks, which are then able to generalize to unseen parts of the game. We use the resulting value network to implement a depth-limited version of counterfactual regret minimization. In three distinct domains, we show that the algorithm's exploitability is roughly linearly dependent on the value network's quality and that it is not difficult to train a value network with which depth-limited CFR's performance is as good as that of CFR with access to the full game.

cs.AI↗

arXiv2021

Rethinking Formal Models of Partially Observable Multiagent Decision Making

Multiagent decision-making in partially observable environments is usually modelled as either an extensive-form game (EFG) in game theory or a partially observable stochastic game (POSG) in multiagent reinforcement learning (MARL). One issue with the current situation is that while most practical problems can be modelled in both formalisms, the relationship of the two models is unclear, which hinders the transfer of ideas between the two communities. A second issue is that while EFGs have recently seen significant algorithmic progress, their classical formalization is unsuitable for efficient presentation of the underlying ideas, such as those around decomposition. To solve the first issue, we introduce factored-observation stochastic games (FOSGs), a minor modification of the POSG formalism which distinguishes between private and public observation and thereby greatly simplifies decomposition. To remedy the second issue, we show that FOSGs and POSGs are naturally connected to EFGs: by "unrolling" a FOSG into its tree form, we obtain an EFG. Conversely, any perfect-recall timeable EFG corresponds to some underlying FOSG in this manner. Moreover, this relationship justifies several minor modifications to the classical EFG formalization that recently appeared as an implicit response to the model's issues with decomposition. Finally, we illustrate the transfer of ideas between EFGs and MARL by presenting three key EFG techniques -- counterfactual regret minimization, sequence form, and decomposition -- in the FOSG framework.

cs.AI↗

arXiv2020

Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Games

Solution concepts of traditional game theory assume entirely rational players; therefore, their ability to exploit subrational opponents is limited. One type of subrationality that describes human behavior well is the quantal response. While there exist algorithms for computing solutions against quantal opponents, they either do not scale or may provide strategies that are even worse than the entirely-rational Nash strategies. This paper aims to analyze and propose scalable algorithms for computing effective and robust strategies against a quantal opponent in normal-form and extensive-form games. Our contributions are: (1) we define two different solution concepts related to exploiting quantal opponents and analyze their properties; (2) we prove that computing these solutions is computationally hard; (3) therefore, we evaluate several heuristic approximations based on scalable counterfactual regret minimization (CFR); and (4) we identify a CFR variant that exploits the bounded opponents better than the previously used variants while being less exploitable by the worst-case perfectly-rational opponent.

cs.AI↗

arXiv2019

Classification with Costly Features as a Sequential Decision-Making Problem

This work focuses on a specific classification problem, where the information about a sample is not readily available, but has to be acquired for a cost, and there is a per-sample budget. Inspired by real-world use-cases, we analyze average and hard variations of a directly specified budget. We postulate the problem in its explicit formulation and then convert it into an equivalent MDP, that can be solved with deep reinforcement learning. Also, we evaluate a real-world inspired setting with sparse training dataset with missing features. The presented method performs robustly well in all settings across several distinct datasets, outperforming other prior-art algorithms. The method is flexible, as showcased with all mentioned modifications and can be improved with any domain independent advancement in RL.

cs.LG↗