A significant challenge for autonomous cyber defence is ensuring a defensive agent's ability to generalise across diverse network topologies and configurations. This capability is necessary for agents to remain effective when deployed in dynamically changing environments, such as an enterprise network where devices may frequently join and leave. Standard approaches to deep reinforcement learning, where policies are parameterised using a fixed-input multi-layer perceptron (MLP) expect fixed-size observation and action spaces. In autonomous cyber defence, this makes it hard to develop agents that generalise to environments with network topologies different from those trained on, as the number of nodes affects the natural size of the observation and action spaces. To overcome this limitation, we reframe the problem of autonomous network defence using entity-based reinforcement learning, where the observation and action space of an agent are decomposed into a collection of discrete entities. This framework enables the use of policy parameterisations specialised in compositional generalisation. We train a Transformer-based policy on the Yawning Titan cyber-security simulation environment and test its generalisation capabilities across various network topologies. We demonstrate that this approach significantly outperforms an MLP-based policy when training across fixed-size networks of varying topologies, and matches performance when training on a single network. We also demonstrate the potential for zero-shot generalisation to networks of a different size to those seen in training. These findings highlight the potential for entity-based reinforcement learning to advance the field of autonomous cyber defence by providing more generalisable policies capable of handling variations in real-world network environments.
Ensuring verifiable and interpretable safety of deep reinforcement learning (DRL) is crucial for its deployment in real-world applications. Existing approaches like verification-in-the-loop training, however, face challenges such as difficulty in deployment, inefficient training, lack of interpretability, and suboptimal performance in property satisfaction and reward performance. In this work, we propose a novel verification-driven interpretation-in-the-loop framework Reintrainer to develop trustworthy DRL models, which are guaranteed to meet the expected constraint properties. Specifically, in each iteration, this framework measures the gap between the on-training model and predefined properties using formal verification, interprets the contribution of each input feature to the model's output, and then generates the training strategy derived from the on-the-fly measure results, until all predefined properties are proven. Additionally, the low reusability of existing verifiers and interpreters motivates us to develop Reinfier, a general and fundamental tool within Reintrainer for DRL verification and interpretation. Reinfier features breakpoints searching and verification-driven interpretation, associated with a concise constraint-encoding language DRLP. Evaluations demonstrate that Reintrainer outperforms the state-of-the-art on six public benchmarks in both performance and property guarantees. Our framework can be accessed at https://github.com/Kurayuri/Reinfier.
Deep Reinforcement learning (DRL) is used to enable autonomous navigation in unknown environments. Most research assume perfect sensor data, but real-world environments may contain natural and artificial sensor noise and denial. Here, we present a benchmark of both well-used and emerging DRL algorithms in a navigation task with configurable sensor denial effects. In particular, we are interested in comparing how different DRL methods (e.g. model-free PPO vs. model-based DreamerV3) are affected by sensor denial. We show that DreamerV3 outperforms other methods in the visual end-to-end navigation task with a dynamic goal - and other methods are not able to learn this. Furthermore, DreamerV3 generally outperforms other methods in sensor-denied environments. In order to improve robustness, we use adversarial training and demonstrate an improved performance in denied environments, although this generally comes with a performance cost on the vanilla environments. We anticipate this benchmark of different DRL methods and the usage of adversarial training to be a starting point for the development of more elaborate navigation strategies that are capable of dealing with uncertain and denied sensor readings.
This paper tackles the challenge of learning non-Markovian optimal execution strategies in dynamic financial markets. We introduce a novel actor-critic algorithm based on Deep Deterministic Policy Gradient (DDPG) to address this issue, with a focus on transient price impact modeled by a general decay kernel. Through numerical experiments with various decay kernels, we show that our algorithm successfully approximates the optimal execution strategy. Additionally, the proposed algorithm demonstrates adaptability to evolving market conditions, where parameters fluctuate over time. Our findings also show that modern reinforcement learning algorithms can provide a solution that reduces the need for frequent and inefficient human intervention in optimal execution tasks.
We demonstrate that recent advances in reinforcement learning (RL) combined with simple architectural changes significantly improves generalization on the ProcGen benchmark. These changes are frame stacking, replacing 2D convolutional layers with 3D convolutional layers, and scaling up the number of convolutional kernels per layer. Experimental results using a single set of hyperparameters across all environments show a 37.9\% reduction in the optimality gap compared to the baseline (from 0.58 to 0.36). This performance matches or exceeds current state-of-the-art methods. The proposed changes are largely orthogonal and therefore complementary to the existing approaches for improving generalization in RL, and our results suggest that further exploration in this direction could yield substantial improvements in addressing generalization challenges in deep reinforcement learning.
Two-stage object detectors exhibit high accuracy and precise localization, especially for identifying small objects that are favorable for various edge applications. However, the high computation costs associated with two-stage detection methods cause more severe thermal issues on edge devices, incurring dynamic runtime frequency change and thus large inference latency variations. Furthermore, the dynamic number of proposals in different frames leads to various computations over time, resulting in further latency variations. The significant latency variations of detectors on edge devices can harm user experience and waste hardware resources. To avoid thermal throttling and provide stable inference speed, we propose Lotus, a novel framework that is tailored for two-stage detectors to dynamically scale CPU and GPU frequencies jointly in an online manner based on deep reinforcement learning (DRL). To demonstrate the effectiveness of Lotus, we implement it on NVIDIA Jetson Orin Nano and Mi 11 Lite mobile platforms. The results indicate that Lotus can consistently and significantly reduce latency variation, achieve faster inference, and maintain lower CPU and GPU temperatures under various settings.
Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to overfitting. These large networks avoid overfitting by integrating components that induce a simplicity bias, guiding models toward simple and generalizable solutions. However, in deep RL, designing and scaling up networks have been less explored. Motivated by this opportunity, we present SimBa, an architecture designed to scale up parameters in deep RL by injecting a simplicity bias. SimBa consists of three components: (i) an observation normalization layer that standardizes inputs with running statistics, (ii) a residual feedforward block to provide a linear pathway from the input to output, and (iii) a layer normalization to control feature magnitudes. By scaling up parameters with SimBa, the sample efficiency of various deep RL algorithms-including off-policy, on-policy, and unsupervised methods-is consistently improved. Moreover, solely by integrating SimBa architecture into SAC, it matches or surpasses state-of-the-art deep RL methods with high computational efficiency across DMC, MyoSuite, and HumanoidBench. These results demonstrate SimBa's broad applicability and effectiveness across diverse RL algorithms and environments.
This paper investigates how children learn numbers using the framework of reinforcement learning (RL), with a focus on the impact of language instructions. The motivation for using reinforcement learning stems from its parallels with psychological learning theories in controlled environments. By using state of the art deep reinforcement learning models, we simulate and analyze the effects of various forms of language instructions on number acquisition. Our findings indicate that certain linguistic structures more effectively improve numerical comprehension in RL agents. Additionally, our model predicts optimal sequences for presenting numbers to RL agents which enhance their speed of learning. This research provides valuable insights into the interplay between language and numerical cognition, with implications for both educational strategies and the development of artificial intelligence systems designed to support early childhood learning.
This article targets at unlocking the potentials of a class of prominent generative artificial intelligence (GAI) method, namely diffusion model (DM), for mobile communications. First, a DM-driven communication architecture is proposed, which introduces two key paradigms, i.e., conditional DM and DM-driven deep reinforcement learning (DRL), for wireless data generation and communication management, respectively. Then, we discuss the key advantages of DM-driven communication paradigms. To elaborate further, we explore DM-driven channel generation mechanisms for channel estimation, extrapolation, and feedback in multiple-input multiple-output (MIMO) systems. We showcase the numerical performance of conditional DM using the accurate DeepMIMO channel datasets, revealing its superiority in generating high-fidelity channels and mitigating unforeseen distribution shifts in sophisticated scenes. Furthermore, several DM-driven communication management designs are conceived, which is promising to deal with imperfect channels and task-oriented communications. To inspire future research developments, we highlight the potential applications and open research challenges of DM-driven communications. Code is available at https://github.com/xiaoxiaxusummer/GAI_COMM/
Recent studies reveal that well-performing reinforcement learning (RL) agents in training often lack resilience against adversarial perturbations during deployment. This highlights the importance of building a robust agent before deploying it in the real world. Most prior works focus on developing robust training-based procedures to tackle this problem, including enhancing the robustness of the deep neural network component itself or adversarially training the agent on strong attacks. In this work, we instead study an input transformation-based defense for RL. Specifically, we propose using a variant of vector quantization (VQ) as a transformation for input observations, which is then used to reduce the space of adversarial attacks during testing, resulting in the transformed observations being less affected by attacks. Our method is computationally efficient and seamlessly integrates with adversarial training, further enhancing the robustness of RL agents against adversarial attacks. Through extensive experiments in multiple environments, we demonstrate that using VQ as the input transformation effectively defends against adversarial attacks on the agent's observations.
Autonomous robots are widely utilized for mapping and exploration tasks due to their cost-effectiveness. Multi-robot systems offer scalability and efficiency, especially in terms of the number of robots deployed in more complex environments. These tasks belong to the set of Multi-Robot Informative Path Planning (MRIPP) problems. In this paper, we propose a deep reinforcement learning approach for the MRIPP problem. We aim to maximize the number of discovered stationary targets in an unknown 3D environment while operating under resource constraints (such as path length). Here, each robot aims to maximize discovered targets, avoid unknown static obstacles, and prevent inter-robot collisions while operating under communication and resource constraints. We utilize the centralized training and decentralized execution paradigm to train a single policy neural network. A key aspect of our approach is our coordination graph that prioritizes visiting regions not yet explored by other robots. Our learned policy can be copied onto any number of robots for deployment in more complex environments not seen during training. Our approach outperforms state-of-the-art approaches by at least 26.2% in terms of the number of discovered targets while requiring a planning time of less than 2 sec per step. We present results for more complex environments with up to 64 robots and compare success rates against baseline planners. Our code and trained model are available at - https://github.com/AccGen99/marl_ipp
Reinforcement learning methods have been used to optimize long-term user engagement in recommendation systems. However, existing reinforcement learning-based recommendation systems do not fully exploit the relevance of individual user behavior across different platforms. One potential solution is to aggregate data from various platforms in a centralized location and use the aggregated data for training. However, this approach raises economic and legal concerns, including increased communication costs and potential threats to user privacy. To address these challenges, we propose \textbf{FedSlate}, a federated reinforcement learning recommendation algorithm that effectively utilizes information that is prohibited from being shared at a legal level. We employ the SlateQ algorithm to assist FedSlate in learning users' long-term behavior and evaluating the value of recommended content. We extend the existing application scope of recommendation systems from single-user single-platform to single-user multi-platform and address cross-platform learning challenges by introducing federated learning. We use RecSim to construct a simulation environment for evaluating FedSlate and compare its performance with state-of-the-art benchmark recommendation models. Experimental results demonstrate the superior effects of FedSlate over baseline methods in various environmental settings, and FedSlate facilitates the learning of recommendation strategies in scenarios where baseline methods are completely inapplicable. Code is available at \textit{https://github.com/TianYaDY/FedSlate}.
Recently, AI systems have made remarkable progress in various tasks. Deep Reinforcement Learning(DRL) is an effective tool for agents to learn policies in low-level state spaces to solve highly complex tasks. Researchers have introduced Intrinsic Motivation(IM) to the RL mechanism, which simulates the agent's curiosity, encouraging agents to explore interesting areas of the environment. This new feature has proved vital in enabling agents to learn policies without being given specific goals. However, even though DRL intelligence emerges through a sub-symbolic model, there is still a need for a sort of abstraction to understand the knowledge collected by the agent. To this end, the classical planning formalism has been used in recent research to explicitly represent the knowledge an autonomous agent acquires and effectively reach extrinsic goals. Despite classical planning usually presents limited expressive capabilities, PPDDL demonstrated usefulness in reviewing the knowledge gathered by an autonomous system, making explicit causal correlations, and can be exploited to find a plan to reach any state the agent faces during its experience. This work presents a new architecture implementing an open-ended learning system able to synthesize from scratch its experience into a PPDDL representation and update it over time. Without a predefined set of goals and tasks, the system integrates intrinsic motivations to explore the environment in a self-directed way, exploiting the high-level knowledge acquired during its experience. The system explores the environment and iteratively: (a) discover options, (b) explore the environment using options, (c) abstract the knowledge collected and (d) plan. This paper proposes an alternative approach to implementing open-ended learning architectures exploiting low-level and high-level representations to extend its knowledge in a virtuous loop.
In this research paper, we investigate into a paper named "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" [arXiv:1706.10059]. It is a portfolio management problem which is solved by deep learning techniques. The original paper proposes a financial-model-free reinforcement learning framework, which consists of the Ensemble of Identical Independent Evaluators (EIIE) topology, a Portfolio-Vector Memory (PVM), an Online Stochastic Batch Learning (OSBL) scheme, and a fully exploiting and explicit reward function. Three different instants are used to realize this framework, namely a Convolutional Neural Network (CNN), a basic Recurrent Neural Network (RNN), and a Long Short-Term Memory (LSTM). The performance is then examined by comparing to a number of recently reviewed or published portfolio-selection strategies. We have successfully replicated their implementations and evaluations. Besides, we further apply this framework in the stock market, instead of the cryptocurrency market that the original paper uses. The experiment in the cryptocurrency market is consistent with the original paper, which achieve superior returns. But it doesn't perform as well when applied in the stock market.
Although deep reinforcement learning (DRL) approaches in audio signal processing have seen substantial progress in recent years, audio-driven DRL for tasks such as navigation, gaze control and head-orientation control in the context of human-robot interaction have received little attention. Here, we propose an audio-driven DRL framework in which we utilise deep Q-learning to develop an autonomous agent that orients towards a talker in the acoustic environment based on stereo speech recordings. Our results show that the agent learned to perform the task at a near perfect level when trained on speech segments in anechoic environments (that is, without reverberation). The presence of reverberation in naturalistic acoustic environments affected the agent's performance, although the agent still substantially outperformed a baseline, randomly acting agent. Finally, we quantified the degree of generalization of the proposed DRL approach across naturalistic acoustic environments. Our experiments revealed that policies learned by agents trained on medium or high reverb environments generalized to low reverb environments, but policies learned by agents trained on anechoic or low reverb environments did not generalize to medium or high reverb environments. Taken together, this study demonstrates the potential of audio-driven DRL for tasks such as head-orientation control and highlights the need for training strategies that enable robust generalization across environments for real-world audio-driven DRL applications.
Deep Reinforcement Learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world.
Q-learning is a widely used algorithm in reinforcement learning (RL), but its convergence can be slow, especially when the discount factor is close to one. Successive Over-Relaxation (SOR) Q-learning, which introduces a relaxation factor to speed up convergence, addresses this issue but has two major limitations: In the tabular setting, the relaxation parameter depends on transition probability, making it not entirely model-free, and it suffers from overestimation bias. To overcome these limitations, we propose a sample-based, model-free double SOR Q-learning algorithm. Theoretically and empirically, this algorithm is shown to be less biased than SOR Q-learning. Further, in the tabular setting, the convergence analysis under boundedness assumptions on iterates is discussed. The proposed algorithm is extended to large-scale problems using deep RL. Finally, the tabular version of the proposed algorithm is compared using roulette and grid world environments, while the deep RL version is tested on a maximization bias example and OpenAI Gym environments.
Deep neural networks provide Reinforcement Learning (RL) powerful function approximators to address large-scale decision-making problems. However, these approximators introduce challenges due to the non-stationary nature of RL training. One source of the challenges in RL is that output predictions can churn, leading to uncontrolled changes after each batch update for states not included in the batch. Although such a churn phenomenon exists in each step of network training, how churn occurs and impacts RL remains under-explored. In this work, we start by characterizing churn in a view of Generalized Policy Iteration with function approximation, and we discover a chain effect of churn that leads to a cycle where the churns in value estimation and policy improvement compound and bias the learning dynamics throughout the iteration. Further, we concretize the study and focus on the learning issues caused by the chain effect in different settings, including greedy action deviation in value-based methods, trust region violation in proximal policy optimization, and dual bias of policy value in actor-critic methods. We then propose a method to reduce the chain effect across different settings, called Churn Approximated ReductIoN (CHAIN), which can be easily plugged into most existing DRL algorithms. Our experiments demonstrate the effectiveness of our method in both reducing churn and improving learning performance across online and offline, value-based and policy-based RL settings, as well as a scaling setting.
Reinforcement Learning (RL) is a learning paradigm in which the agent learns from its environment through trial and error. Deep reinforcement learning (DRL) algorithms represent the agent's policies using neural networks, making their decisions difficult to interpret. Explaining the behaviour of DRL agents is necessary to advance user trust, increase engagement, and facilitate integration with real-life tasks. Semifactual explanations aim to explain an outcome by providing "even if" scenarios, such as "even if the car were moving twice as slowly, it would still have to swerve to avoid crashing". Semifactuals help users understand the effects of different factors on the outcome and support the optimisation of resources. While extensively studied in psychology and even utilised in supervised learning, semifactuals have not been used to explain the decisions of RL systems. In this work, we develop a first approach to generating semifactual explanations for RL agents. We start by defining five properties of desirable semifactual explanations in RL and then introducing SGRL-Rewind and SGRL-Advance, the first algorithms for generating semifactual explanations in RL. We evaluate the algorithms in two standard RL environments and find that they generate semifactuals that are easier to reach, represent the agent's policy better, and are more diverse compared to baselines. Lastly, we conduct and analyse a user study to assess the participant's perception of semifactual explanations of the agent's actions.
Recent advances in deep reinforcement learning have achieved impressive results in a wide range of complex tasks, but poor sample efficiency remains a major obstacle to real-world deployment. Soft actor-critic (SAC) mitigates this problem by combining stochastic policy optimization and off-policy learning, but its applicability is restricted to distributions whose gradients can be computed through the reparameterization trick. This limitation excludes several important examples such as the beta distribution, which was shown to improve the convergence rate of actor-critic algorithms in high-dimensional continuous control problems thanks to its bounded support. To address this issue, we investigate the use of implicit reparameterization, a powerful technique that extends the class of reparameterizable distributions. In particular, we use implicit reparameterization gradients to train SAC with the beta policy on simulated robot locomotion environments and compare its performance with common baselines. Experimental results show that the beta policy is a viable alternative, as it outperforms the normal policy and is on par with the squashed normal policy, which is the go-to choice for SAC. The code is available at https://github.com/lucadellalib/sac-beta.