Advancements in reinforcement learning (RL) have inspired new directions in intelligent automation of network defense. However, many of these advancements have either outpaced their application to network security or have not considered the challenges associated with implementing them in the real-world. To understand these problems, this work evaluates several RL approaches implemented in the second edition of the CAGE Challenge, a public competition to build an autonomous network defender agent in a high-fidelity network simulator. Our approaches all build on the Proximal Policy Optimization (PPO) family of algorithms, and include hierarchical RL, action masking, custom training, and ensemble RL. We find that the ensemble RL technique performs strongest, outperforming our other models and taking second place in the competition. To understand applicability to real environments we evaluate each method's ability to generalize to unseen networks and against an unknown attack strategy. In unseen environments, all of our approaches perform worse, with degradation varied based on the type of environmental change. Against an unknown attacker strategy, we found that our models had reduced overall performance even though the new strategy was less efficient than the ones our models trained on.

We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensionality and to reduce communication, we propose a Localized Policy Iteration (LPI) algorithm that provably learns a near-globally-optimal policy using only local information. In particular, we show that, despite restricting each agent's attention to only its $\kappa$-hop neighborhood, the agents are able to learn a policy with an optimality gap that decays polynomially in $\kappa$. In addition, we show the finite-sample convergence of LPI to the global optimal policy, which explicitly captures the trade-off between optimality and computational complexity in choosing $\kappa$. Numerical simulations demonstrate the effectiveness of LPI.

In this paper, we identify the best learning scenario to train a team of agents to compete against multiple possible strategies of opposing teams. We evaluate cooperative value-based methods in a mixed cooperative-competitive environment. We restrict ourselves to the case of a symmetric, partially observable, two-team Markov game. We selected three training methods based on the centralised training and decentralised execution (CTDE) paradigm: QMIX, MAVEN and QVMix. For each method, we considered three learning scenarios differentiated by the variety of team policies encountered during training. For our experiments, we modified the StarCraft Multi-Agent Challenge environment to create competitive environments where both teams could learn and compete simultaneously. Our results suggest that training against multiple evolving strategies achieves the best results when, for scoring their performances, teams are faced with several strategies.

Communication enables agents to cooperate to achieve their goals. Learning when to communicate, i.e., sparse (in time) communication, and whom to message is particularly important when bandwidth is limited. Recent work in learning sparse individualized communication, however, suffers from high variance during training, where decreasing communication comes at the cost of decreased reward, particularly in cooperative tasks. We use the information bottleneck to reframe sparsity as a representation learning problem, which we show naturally enables lossless sparse communication at lower budgets than prior art. In this paper, we propose a method for true lossless sparsity in communication via Information Maximizing Gated Sparse Multi-Agent Communication (IMGS-MAC). Our model uses two individualized regularization objectives, an information maximization autoencoder and sparse communication loss, to create informative and sparse communication. We evaluate the learned communication `language' through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity. To demonstrate the efficacy of our results, we experiment in cooperative multi-agent tasks where communication is essential for success. We evaluate our model with both continuous and discrete messages. We focus our analysis on a variety of ablations to show the effect of message representations, including their properties, and lossless performance of our model.

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of approaches to explainability in RL that aim to reconcile discrepancies that may arise between the behavior of an agent and the behavior that is anticipated by an observer. Most recent approaches have relied either on domain knowledge that may not always be available, on an analysis of the agent's policy, or on an analysis of specific elements of the underlying environment, typically modeled as a Markov Decision Process (MDP). Our key claim is that even if the underlying model is not fully known (e.g., the transition probabilities have not been accurately learned) or is not maintained by the agent (i.e., when using model-free methods), the model can nevertheless be exploited to automatically generate explanations. For this purpose, we suggest using formal MDP abstractions and transforms, previously used in the literature for expediting the search for optimal policies, to automatically produce explanations. Since such transforms are typically based on a symbolic representation of the environment, they can provide meaningful explanations for gaps between the anticipated and actual agent behavior. We formally define the explainability problem, suggest a class of transforms that can be used for explaining emergent behaviors, and suggest methods that enable efficient search for an explanation. We demonstrate the approach on a set of standard benchmarks.

Information is often stored in a distributed and proprietary form, and agents who own information are often self-interested and require incentives to reveal their information. Suitable mechanisms are required to elicit and aggregate such distributed information for decision making. In this paper, we use simulations to investigate the use of decision markets as mechanisms in a multi-agent learning system to aggregate distributed information for decision-making in a contextual bandit problem. The system utilises strictly proper decision scoring rules to assess the accuracy of probabilistic reports from agents, which allows agents to learn to solve the contextual bandit problem jointly. Our simulations show that our multi-agent system with distributed information can be trained as efficiently as a centralised counterpart with a single agent that receives all information. Moreover, we use our system to investigate scenarios with deterministic decision scoring rules which are not incentive compatible. We observe the emergence of more complex dynamics with manipulative behaviour, which agrees with existing theoretical analyses.

Voting is used widely to identify a collective decision for a group of agents, based on their preferences. In this paper, we focus on evaluating and designing voting rules that support both the privacy of the voting agents and a notion of fairness over such agents. To do this, we introduce a novel notion of group fairness and adopt the existing notion of local differential privacy. We then evaluate the level of group fairness in several existing voting rules, as well as the trade-offs between fairness and privacy, showing that it is not possible to always obtain maximal economic efficiency with high fairness or high privacy levels. Then, we present both a machine learning and a constrained optimization approach to design new voting rules that are fair while maintaining a high level of economic efficiency. Finally, we empirically examine the effect of adding noise to create local differentially private voting rules and discuss the three-way trade-off between economic efficiency, fairness, and privacy. This paper appears in the special track on AI & Society.

We develop a wall model for large-eddy simulation (LES) that takes into account various pressure-gradient effects using multi-agent reinforcement learning (MARL). The model is trained using low-Reynolds-number flow over periodic hills with agents distributed on the wall along the computational grid points. The model utilizes a wall eddy-viscosity formulation as the boundary condition, which is shown to provide better predictions of the mean velocity field, rather than the typical wall-shear stress formulation. Each agent receives states based on local instantaneous flow quantities at an off-wall location, computes a reward based on the estimated wall-shear stress, and provides an action to update the wall eddy viscosity at each time step. The trained wall model is validated in wall-modeled LES (WMLES) of flow over periodic hills at higher Reynolds numbers, and the results show the effectiveness of the model on flow with pressure gradients. The analysis of the trained model indicates that the model is capable of distinguishing between the various pressure gradient regimes present in the flow.

We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. Such game access is common in reinforcement learning settings, where the environment is typically treated as a black box. To tackle this problem, we apply zeroth-order optimization techniques that combine smoothed gradient estimators with equilibrium-finding dynamics. We model players' strategies using artificial neural networks. In particular, we use randomized policy networks to model mixed strategies. These take noise in addition to an observation as input and can flexibly represent arbitrary observation-dependent, continuous-action distributions. Being able to model such mixed strategies is crucial for tackling continuous-action games that lack pure-strategy equilibria. We evaluate the performance of our method using an approximation of the Nash convergence metric from game theory, which measures how much players can benefit from unilaterally changing their strategy. We apply our method to continuous Colonel Blotto games, single-item and multi-item auctions, and a visibility game. The experiments show that our method can quickly find high-quality approximate equilibria. Furthermore, they show that the dimensionality of the input noise is crucial for performance. To our knowledge, this paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.

Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. As the systems grow in complexity, fine-tuning architectural parameters across multiple sub-systems (e.g., datapath, memory blocks in different hierarchies, interconnects, compiler optimization, etc.) quickly results in a combinatorial explosion of design space. This makes domain-specific customization an extremely challenging task. Prior work explores using reinforcement learning (RL) and other optimization methods to automatically explore the large design space. However, these methods have traditionally relied on single-agent RL/ML formulations. It is unclear how scalable single-agent formulations are as we increase the complexity of the design space (e.g., full stack System-on-Chip design). Therefore, we propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. The key idea behind using MARL is an observation that parameters across different sub-systems are more or less independent, thus allowing a decentralized role assigned to each agent. We test this hypothesis by designing domain-specific DRAM memory controller for several workload traces. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines such as Proximal Policy Optimization and Soft Actor-Critic over different target objectives such as low power and latency. To this end, this work opens the pathway for new and promising research in MARL solutions for hardware architecture search.