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.

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.

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.

Fast Algorithms for Poker Require Modelling it as a Sequential Bayesian Game

Many recent results in imperfect information games were only formulated for, or evaluated on, poker and poker-like games such as liar's dice. We argue that sequential Bayesian games constitute a natural class of games for generalizing these results. In particular, this model allows for an elegant formulation of the counterfactual regret minimization algorithm, called public-state CFR (PS-CFR), which naturally lends itself to an efficient implementation. Empirically, solving a poker subgame with 10^7 states by public-state CFR takes 3 minutes and 700 MB while a comparable version of vanilla CFR takes 5.5 hours and 20 GB. Additionally, the public-state formulation of CFR opens up the possibility for exploiting domain-specific assumptions, leading to a quadratic reduction in asymptotic complexity (and a further empirical speedup) over vanilla CFR in poker and other domains. Overall, this suggests that the ability to represent poker as a sequential Bayesian game played a key role in the success of CFR-based methods. Finally, we extend public-state CFR to general extensive-form games, arguing that this extension enjoys some - but not all - of the benefits of the version for sequential Bayesian games.

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.

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks

We present a novel deep reinforcement learning framework for solving relational problems. The method operates with a symbolic representation of objects, their relations and multi-parameter actions, where the objects are the parameters. Our framework, based on graph neural networks, is completely domain-independent and can be applied to any relational problem with existing symbolic-relational representation. We show how to represent relational states with arbitrary goals, multi-parameter actions and concurrent actions. We evaluate the method on a set of three domains: BlockWorld, Sokoban and SysAdmin. The method displays impressive generalization over different problem sizes (e.g., in BlockWorld, the method trained exclusively with 5 blocks still solves 78% of problems with 20 blocks) and readiness for curriculum learning.

Deep Reinforcement Learning with Explicitly Represented Knowledge and Variable State and Action Spaces

We focus on a class of real-world domains, where gathering hierarchical knowledge is required to accomplish a task. Many problems can be represented in this manner, such as network penetration testing, targeted advertising or medical diagnosis. In our formalization, the task is to sequentially request pieces of information about a sample to build the knowledge hierarchy and terminate when suitable. Any of the learned pieces of information can be further analyzed, resulting in a complex and variable action space. We present a combination of techniques in which the knowledge hierarchy is explicitly represented and given to a deep reinforcement learning algorithm as its input. To process the hierarchical input, we employ Hierarchical Multiple-Instance Learning and to cope with the complex action space, we factor it with hierarchical softmax. Our end-to-end differentiable model is trained with A2C, a standard deep reinforcement learning algorithm. We demonstrate the method in a set of seven classification domains, where the task is to achieve the best accuracy with a set budget on the amount of information retrieved. Compared to baseline algorithms, our method achieves not only better results, but also better generalization.

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.

Rethinking Formal Models of Partially Observable Multiagent Decision Making

Multiagent decision-making problems in partially observable environments are usually modeled as either extensive-form games (EFGs) within the game theory community or partially observable stochastic games (POSGs) within the reinforcement learning community. While most practical problems can be modeled in both formalisms, the communities using these models are mostly distinct with little sharing of ideas or advances. The last decade has seen dramatic progress in algorithms for EFGs, mainly driven by the challenge problem of poker. We have seen computational techniques achieving super-human performance, some variants of poker are essentially solved, and there are now sound local search algorithms which were previously thought impossible. While the advances have garnered attention, the fundamental advances are not yet understood outside the EFG community. This can be largely explained by the starkly different formalisms between the game theory and reinforcement learning communities and, further, by the unsuitability of the original EFG formalism to make the ideas simple and clear. This paper aims to address these hindrances, by advocating a new unifying formalism, a variant of POSGs, which we call Factored-Observation Games (FOGs). We prove that any timeable perfect-recall EFG can be efficiently modeled as a FOG as well as relating FOGs to other existing formalisms. Additionally, a FOG explicitly identifies the public and private components of observations, which is fundamental to the recent EFG breakthroughs. We conclude by presenting the two building-blocks of these breakthroughs --- counterfactual regret minimization and public state decomposition --- in the new formalism, illustrating our goal of a simpler path for sharing recent advances between game theory and reinforcement learning community.

Classification with Costly Features using Deep Reinforcement Learning

We study a classification problem where each feature can be acquired for a cost and the goal is to optimize the trade-off between classification precision and the total feature cost. We frame the problem as a sequential decision-making problem, where we classify one sample in each episode. At each step, an agent can use values of acquired features to decide whether to purchase another one or whether to classify the sample. We use vanilla Double Deep Q-learning, a standard reinforcement learning technique, to find a classification policy. We show that this generic approach outperforms Adapt-Gbrt, currently the best-performing algorithm developed specifically for classification with costly features.