Reinforcement Learning Environment Research Articles

RCI-Seg: Robust click-based interactive segmentation framework with deep reinforcement learning for biomedical images

Recently, interactive segmentation models have achieved remarkable success in the field of biomedical images. However, these models rely on the accurate and high-quality interaction information provided by users, otherwise the segmentation performance will be seriously affected. This problem is more severe in multi-target biomedical images, which means that an image contains multiple targets of interest. It is extremely challenging for users to always maintain high-quality interactions. In this paper, we propose a novel two-stage segmentation model with robust interaction points for biomedical images. In the first stage, we implement robust interaction points based on user initial interaction points and the deep reinforcement learning (DRL) model. Specifically, we build a reinforcement learning environment to simulate the movement of interaction points with agents, and obtain improved interaction points (clue points) that are beneficial for segmentation. In the second stage, we use a convolutional neural network (CNN) model to achieve segmentation by combining clue points and biomedical image. We validate the performance of our approach on five public biomedical image datasets. The experimental results show that the proposed approach outperforms several SOTA methods in multiple metrics.

An innovative multi-agent approach for robust cyber–physical systems using vertical federated learning

Federated learning presents a compelling approach to training artificial intelligence systems in decentralized settings, prioritizing data safety over traditional centralized training methods. Understanding correlations among higher-level threats exhibiting abnormal behavior in the data stream becomes paramount to developing cyber–physical systems resilient to diverse attacks within a continuous data exchange framework. This work introduces a novel vertical federated multi-agent learning framework to address the challenges of modeling attacker and defender agents in stationary and non-stationary vertical federated learning environments. Our approach uniquely applies synchronous Deep Q-Network (DQN) based agents in stationary environments, facilitating convergence towards optimal strategies. Conversely, in non-stationary contexts, we employ synchronous Advantage Actor–Critic (A2C) based agents, adapting to the dynamic nature of multi-agent vertical federated reinforcement learning (VFRL) environments. This methodology enables us to simulate and analyze the adversarial interplay between attacker and defender agents, ensuring robust policy development. Our exhaustive analysis demonstrates the effectiveness of our approach, showcasing its capability to learn optimal policies in both static and dynamic setups, thus significantly advancing the field of cyber-security in federated learning contexts. To evaluate the effectiveness of our approach, we have done a comparative analysis with its baseline schemes. The findings of our study show significant enhancements compared to the standard methods, confirming the efficacy of our methodology. This progress dramatically enhances the area of cyber-security in the context of federated learning by facilitating the formulation of substantial policies. The proposed scheme attains 15.93%, 32.91%, 31.02%, and 47.26% higher results as compared to the A3C, DDQN, DQN, and Reinforce, respectively.

Offloading Strategy Based on Graph Neural Reinforcement Learning in Mobile Edge Computing

In the mobile edge computing (MEC) architecture, base stations with computational capabilities are subject to service coverage limitations, and the mobility of devices leads to dynamic changes in their connections, directly impacting the offloading decisions of agents. The connections between base stations and mobile devices, as well as the connections between base stations themselves, are abstracted into an MEC structural diagram due to the difficulty of deep reinforcement learning (DRL) in capturing the complex relationships between nodes and their multi-order neighboring nodes in the graph; decisions solely generated by DRL have limitations. To address this issue, this study proposes a hierarchical mechanism strategy based on Graph Neural Reinforcement Learning (M-GNRL) under multiple constraints. Specifically, the MEC structural graph constructed with the current device as an observation point aggregates to learn node features, thus comprehensively considering the contextual information of nodes, and the learned graph information serves as the environment for deep reinforcement learning, effectively integrating a graph neural network (GNN) with DRL. In the M-GNRL strategy, edge features from GNN are introduced into the architecture of the DRL network to enhance the accuracy of agents’ decision-making. Additionally, this study proposes an updated algorithm to obtain graph data that change with observation points. Comparative experiments demonstrate that the M-GNRL algorithm outperforms other baseline algorithms in terms of system cost and convergence performance.

AutoRL X: Automated Reinforcement Learning on the Web

Reinforcement Learning (RL) is crucial in decision optimization, but its inherent complexity often presents challenges in interpretation and communication. Building upon AutoDOViz — an interface that pushed the boundaries of Automated RL for Decision Optimization — this paper unveils an open-source expansion with a web-based platform for RL. Our work introduces a taxonomy of RL visualizations and launches a dynamic web platform, leveraging backend flexibility for AutoRL frameworks like ARLO and Svelte.js for a smooth interactive user experience in the front end. Since AutoDOViz is not open-source, we present AutoRL X, a new interface designed to visualize RL processes. AutoRL X is shaped by the extensive user feedback and expert interviews from AutoDOViz studies, and it brings forth an intelligent interface with real-time, intuitive visualization capabilities that enhance understanding, collaborative efforts, and personalization of RL agents. Addressing the gap in accurately representing complex real-world challenges within standard RL environments, we demonstrate our tool's application in healthcare, explicitly optimizing brain stimulation trajectories. A user study contrasts the performance of human users optimizing electric fields via a 2D interface with RL agents’ behavior that we visually analyze in AutoRL X, assessing the practicality of automated RL. All our data and code is openly available at: https://github.com/lorifranke/autorlx .

Optimal Operation of Cryogenic Calorimeters Through Deep Reinforcement Learning

Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to sub-GeV/c2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^2$$\\end{document} dark matter interactions with nuclei in current direct detection experiments. In such devices, the temperature of the thermometer and the bias current in its readout circuit need careful optimization to achieve optimal detector performance. This task is not trivial and is typically done manually by an expert. In our work, we automated the procedure with reinforcement learning in two settings. First, we trained on a simulation of the response of three Cryogenic Rare Event Search with Superconducting Thermometers (CRESST) detectors used as a virtual reinforcement learning environment. Second, we trained live on the same detectors operated in the CRESST underground setup. In both cases, we were able to optimize a standard detector as fast and with comparable results as human experts. Our method enables the tuning of large-scale cryogenic detector setups with minimal manual interventions.

Modeling Bellman-error with logistic distribution with applications in reinforcement learning

In modern Reinforcement Learning (RL) approaches, optimizing the Bellman error is a critical element across various algorithms, notably in deep Q-Learning and related methodologies. Traditional approaches predominantly employ the mean-squared Bellman error (MSELoss) as the standard loss function. However, the assumption of Bellman errors following the Gaussian distribution may oversimplify the nuanced characteristics of RL applications. In this work, we revisit the distribution of Bellman error in RL training, demonstrating that it tends to follow the Logistic distribution rather than the commonly assumed Normal distribution. We propose replacing MSELoss with a Logistic maximum likelihood function (LLoss) and rigorously test this hypothesis through extensive numerical experiments across diverse online and offline RL environments. Our findings consistently show that integrating the Logistic correction into the loss functions of various baseline RL methods leads to superior performance compared to their MSE counterparts. Additionally, we employ Kolmogorov–Smirnov tests to substantiate that the Logistic distribution offers a more accurate fit for approximating Bellman errors. This study also offers a novel theoretical contribution by establishing a clear connection between the distribution of Bellman error and the practice of proportional reward scaling, a common technique for performance enhancement in RL. Moreover, we explore the sample-accuracy trade-off involved in approximating the Logistic distribution, leveraging the Bias–Variance decomposition to mitigate excessive computational resources. The theoretical and empirical insights presented in this study lay a significant foundation for future research, potentially advancing methodologies, and understanding in RL, particularly in the distribution-based optimization of Bellman error.

Automatic evolutionary design of quantum rule-based systems and applications to quantum reinforcement learning

Explainable artificial intelligence is a research topic whose relevance has increased in recent years, especially with the advent of large machine learning models. However, very few attempts have been proposed to improve interpretability in the case of quantum artificial intelligence, and many existing quantum machine learning models in the literature can be considered almost as black boxes. In this article, we argue that an appropriate semantic interpretation of a given quantum circuit that solves a problem can be of interest to the user not only to certify the correct behavior of the learned model, but also to obtain a deeper insight into the problem at hand and its solution. We focus on decision-making problems that can be formulated as classification tasks and propose a method for learning quantum rule-based systems to solve them using evolutionary optimization algorithms. The approach is tested to learn rules that solve control and decision-making tasks in reinforcement learning environments, to provide interpretable agent policies that help to understand the internal dynamics of an unknown environment. Our results conclude that the learned policies are not only highly explainable, but can also help detect non-relevant features of problems and produce a minimal set of rules.

The quantum cartpole: A benchmark environment for non-linear reinforcement learning

Feedback-based control is the de-facto standard when it comes to controlling classical stochastic systems and processes. However, standard feedback-based control methods are challenged by quantum systems due to measurement induced backaction and partial observability. Here we remedy this by using weak quantum measurements and model-free reinforcement learning agents to perform quantum control. By comparing control algorithms with and without state estimators to stabilize a quantum particle in an unstable state near a local potential energy maximum, we show how a trade-off between state estimation and controllability arises. For the scenario where the classical analogue is highly nonlinear, the reinforcement learned controller has an advantage over the standard controller. Additionally, we demonstrate the feasibility of using transfer learning to develop a quantum control agent trained via reinforcement learning on a classical surrogate of the quantum control problem. Finally, we present results showing how the reinforcement learning control strategy differs from the classical controller in the non-linear scenarios.

Partially observable deep reinforcement learning for multi-agent strategy optimization of human-robot collaborative disassembly: A case of retired electric vehicle battery

The burgeoning electric vehicle (EV) industry has precipitated a commensurate surge in the consumption of EV batteries, which are currently labor-intensive and inefficient for the recycling and disassembly of EV batteries. However, it is a potential trend to enhance the efficacy and safety of the disassembly of EV batteries based on human-robot collaboration (HRC) method. Because of the uncertainty of retired EV battery disassembly and the inefficiency of the existing disassembling sequence, it is difficult to be fully accomplish through HRC disassembly. The collaborative disassembly of EV batteries by humans and robots can be conceptualized as agents engaging with and learning from the environment, and modeled as a multi-agent Markov game process. This paper aims to address the challenge of HRC in the disassembly of EV batteries by recognizing the dual attributes of partial observability and non-smoothness in the suitable disassembly scenario. A partially observable multi-agent reinforcement learning environment is constructed, incorporating the structural aspects of the EV battery and the disassembly task. The framework is extended to the QMIX-HRC algorithm on the QMIX architecture (as a value-based multi-agent deep reinforcement learning algorithm), specifically designed to tackle the sequence problem in human-robot collaborative disassembly of EV batteries. The optimization results would yield a task sequence to offer maximal global co-benefit during the exploration iteration, facilitating a reduction in labor costs and an enhancement of co-efficiency. The viability of the QMIX-HRC disassembly strategy would be verified through the eventual disassembly sequence of a simulated battery pack through a real human-robot collaborative disassembly station.

Humans adaptively select different computational strategies in different learning environments.

The Rescorla-Wagner rule remains the most popular tool to describe human behavior in reinforcement learning tasks. Nevertheless, it cannot fit human learning in complex environments. Previous work proposed several hierarchical extensions of this learning rule. However, it remains unclear when a flat (nonhierarchical) versus a hierarchical strategy is adaptive, or when it is implemented by humans. To address this question, current work applies a nested modeling approach to evaluate multiple models in multiple reinforcement learning environments both computationally (which approach performs best) and empirically (which approach fits human data best). We consider 10 empirical data sets (N = 407) divided over three reinforcement learning environments. Our results demonstrate that different environments are best solved with different learning strategies; and that humans adaptively select the learning strategy that allows best performance. Specifically, while flat learning fitted best in less complex stable learning environments, humans employed more hierarchically complex models in more complex environments. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

FGeo-DRL: Deductive Reasoning for Geometric Problems through Deep Reinforcement Learning

Human-like automatic deductive reasoning has always been one of the most challenging open problems in the interdisciplinary field of mathematics and artificial intelligence. This paper is the third in a series of our works. We built a neural-symbolic system, named FGeo-DRL, to automatically perform human-like geometric deductive reasoning. The neural part is an AI agent based on deep reinforcement learning, capable of autonomously learning problem-solving methods from the feedback of a formalized environment, without the need for human supervision. It leverages a pre-trained natural language model to establish a policy network for theorem selection and employ Monte Carlo Tree Search for heuristic exploration. The symbolic part is a reinforcement learning environment based on geometry formalization theory and FormalGeo, which models geometric problem solving (GPS) as a Markov Decision Process (MDP). In the formal symbolic system, the symmetry of plane geometric transformations ensures the uniqueness of geometric problems when converted into states. Finally, the known conditions and objectives of the problem form the state space, while the set of theorems forms the action space. Leveraging FGeo-DRL, we have achieved readable and verifiable automated solutions to geometric problems. Experiments conducted on the formalgeo7k dataset have achieved a problem-solving success rate of 86.40%.

RayNet: A Simulation Platform for Developing Reinforcement Learning-Driven Network Protocols

Reinforcement Learning (RL) has gained significant momentum in the development of network protocols. However, RL-based protocols are still in their infancy, and substantial research is required to build deployable solutions. Developing a protocol based on RL is a complex and challenging process that involves several model design decisions and requires significant training and evaluation in real and simulated network topologies. Network simulators offer an efficient training environment for RL-based protocols, because they are deterministic and can run in parallel. In this paper, we introduce RayNet , a scalable and adaptable simulation platform for the development of RL-based network protocols. RayNet integrates OMNeT++, a fully programmable network simulator, with Ray/RLlib, a scalable training platform for distributed RL. RayNet facilitates the methodical development of RL-based network protocols so that researchers can focus on the problem at hand and not on implementation details of the learning aspect of their research. We developed a simple RL-based congestion control approach as a proof of concept showcasing that RayNet can be a valuable platform for RL-based research in computer networks, enabling scalable training and evaluation. We compared RayNet with ns3-gym , a platform with similar objectives to RayNet, and showed that RayNet performs better in terms of how fast agents can collect experience in RL environments.

An efficient and adaptive design of reinforcement learning environment to solve job shop scheduling problem with soft actor-critic algorithm

Shop scheduling is deeply involved in manufacturing. In order to improve the efficiency of scheduling and fit dynamic scenarios, many Deep Reinforcement Learning (DRL) methods are studied to solve scheduling problems like job shop and flow shop. But most studies focus on using the latest algorithms while ignoring that the environment plays an important role in agent learning. In this paper, we design an effective, robust and size-agnostic environment for job shop scheduling. The proposed design of environment uses centralised training and decentralised execution (CTDE) to implement a multi-agent architecture. Together with the observation space we design, environmental information that is irrelevant to the current decision is eliminated as much as possible. The proposed action space enlarges the decision space of agents, which performs better than the traditional way. Finally, Soft Actor-Critic (SAC) algorithm is adapted to learning within this environment. By comparing with traditional scheduling rules, other reinforcement learning algorithms, and relevant literature, the superiority of the results obtained in this study is demonstrated.

The CoachAI Badminton Environment: A Novel Reinforcement Learning Environment with Realistic Opponents (Student Abstract)

The growing demand for precise sports analysis has been explored to improve athlete performance in various sports (e.g., basketball, soccer). However, existing methods for different sports face challenges in validating strategies in environments due to simple rule-based opponents leading to performance gaps when deployed in real-world matches. In this paper, we propose the CoachAI Badminton Environment, a novel reinforcement learning (RL) environment with realistic opponents for badminton, which serves as a compelling example of a turn-based game. It supports researchers in exploring various RL algorithms with the badminton context by integrating state-of-the-art tactical-forecasting models and real badminton game records. The Badminton Benchmarks are proposed with multiple widely adopted RL algorithms to benchmark the performance of simulating matches against real players. To advance novel algorithms and developments in badminton analytics, we make our environment open-source, enabling researchers to simulate more complex badminton sports scenarios based on this foundation. Our code is available at https://github.com/wywyWang/CoachAI-Projects/tree/main/CoachAI%20Badminton%20Environment.

The CoachAI Badminton Environment: Bridging the Gap between a Reinforcement Learning Environment and Real-World Badminton Games

We present the CoachAI Badminton Environment, a reinforcement learning (RL) environment tailored for AI-driven sports analytics. In contrast to traditional environments using rule-based opponents or simplistic physics-based randomness, our environment integrates authentic opponent AIs and realistic randomness derived from real-world matches data to bridge the performance gap encountered in real-game deployments. This novel feature enables RL agents to seamlessly adapt to genuine scenarios. The CoachAI Badminton Environment empowers researchers to validate strategies in intricate real-world settings, offering: i) Realistic opponent simulation for RL training; ii) Visualizations for evaluation; and iii) Performance benchmarks for assessing agent capabilities. By bridging the RL environment with actual badminton games, our environment is able to advance the discovery of winning strategies for players. Our code is available at https://github.com/wywyWang/CoachAI-Projects/tree/main/Strategic%20Environment.

Mimicking the Maestro: Exploring the Efficacy of a Virtual AI Teacher in Fine Motor Skill Acquisition

Motor skills, especially fine motor skills like handwriting, play an essential role in academic pursuits and everyday life. Traditional methods to teach these skills, although effective, can be time-consuming and inconsistent. With the rise of advanced technologies like robotics and artificial intelligence, there is increasing interest in automating such teaching processes. In this study, we examine the potential of a virtual AI teacher in emulating the techniques of human educators for motor skill acquisition. We introduce an AI teacher model that captures the distinct characteristics of human instructors. Using a reinforcement learning environment tailored to mimic teacher-learner interactions, we tested our AI model against four guiding hypotheses, emphasizing improved learner performance, enhanced rate of skill acquisition, and reduced variability in learning outcomes. Our findings, validated on synthetic learners, revealed significant improvements across all tested hypotheses. Notably, our model showcased robustness across different learners and settings and demonstrated adaptability to handwriting. This research underscores the potential of integrating Imitation and Reinforcement Learning models with robotics in revolutionizing the teaching of critical motor skills.

Sustainability of Data Center Digital Twins with Reinforcement Learning

The rapid growth of machine learning (ML) has led to an increased demand for computational power, resulting in larger data centers (DCs) and higher energy consumption. To address this issue and reduce carbon emissions, intelligent design and control of DC components such as IT servers, cabinets, HVAC cooling, flexible load shifting, and battery energy storage are essential. However, the complexity of designing and controlling them in tandem presents a significant challenge. While some individual components like CFD-based design and Reinforcement Learning (RL) based HVAC control have been researched, there's a gap in the holistic design and optimization covering all elements simultaneously. To tackle this, we've developed DCRL-Green, a multi-agent RL environment that empowers the ML community to design data centers and research, develop, and refine RL controllers for carbon footprint reduction in DCs. It is a flexible, modular, scalable, and configurable platform that can handle large High Performance Computing (HPC) clusters. Furthermore, in its default setup, DCRL-Green provides a benchmark for evaluating single as well as multi-agent RL algorithms. It easily allows users to subclass the default implementations and design their own control approaches, encouraging community development for sustainable data centers. Open Source Link: https://github.com/HewlettPackard/dc-rl

Intrusion Detection Based on Adaptive Sample Distribution Dual-Experience Replay Reinforcement Learning

In order to cope with ever-evolving and increasing cyber threats, intrusion detection systems have become a crucial component of cyber security. Compared with signature-based intrusion detection methods, anomaly-based methods typically employ machine learning techniques to train detection models and possess the capability to discover unknown attacks. However, intrusion detection methods face the challenge of low detection rates for minority class attacks due to imbalanced data distributions. Traditional intrusion detection algorithms address this issue by resampling or generating synthetic data. Additionally, reinforcement learning, as a machine learning method that interacts with the environment to obtain feedback and improve performance, is gradually being considered for application in the field of intrusion detection. This paper proposes a reinforcement-learning-based intrusion detection method that innovatively uses adaptive sample distribution dual-experience replay to enhance a reinforcement learning algorithm, aiming to effectively address the issue of imbalanced sample distribution. We have also developed a reinforcement learning environment specifically designed for intrusion detection tasks. Experimental results demonstrate that the proposed model achieves favorable performance on the NSL-KDD, AWID, and CICIoT2023 datasets, effectively dealing with imbalanced data and showing better classification performance in detecting minority attacks.

Causal Meta-Reinforcement Learning for Multimodal Remote Sensing Data Classification

Multimodal remote sensing data classification can enhance a model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks has become the focus of researchers. Inspired by the human feedback learning mechanism, causal reasoning mechanism, and knowledge induction mechanism, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposes causal meta-reinforcement learning (CMRL). First, based on the feedback learning mechanism, we overcame the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we helped the agents understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information.Second, based on the causal inference mechanism, we designed causal distribution prediction actions, classification rewards, and causal intervention rewards, capturing pure causal factors in multimodal data and preventing false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets showed that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

An automated energy management framework for smart homes

Over the last fifty years, societies across the world have experienced multiple periods of energy insufficiency with the most recent one being the 2022 global energy crisis. In addition, the electric power industry has been experiencing a steady increase in electricity consumption since the second industrial revolution because of the widespread usage of electrical appliances and devices. Newer devices are equipped with sensors and actuators, they can collect a large amount of data that could help in power management. However, current energy management approaches are mostly applied to limited types of devices in specific domains and are difficult to implement in other scenarios. They fail when it comes to their level of autonomy, flexibility, and genericity. To address these shortcomings, we present, in this paper, an automated energy management approach for connected environments based on generating power estimation models, representing a formal description of energy-related knowledge, and using reinforcement learning (RL) techniques to accomplish energy-efficient actions. The architecture of this approach is based on three main components: power estimation models, knowledge base, and intelligence module. Furthermore, we develop algorithms that exploit knowledge from both the power estimator and the ontology, to generate the corresponding RL agent and environment. We also present different reward functions based on user preferences and power consumption. We illustrate our proposal in the smart home domain. An implementation of the approach is developed and two validation experiments are conducted. Both case studies are deployed in the context of smart homes: (a) a living room with a variety of devices and (b) a smart home with a heating system. The obtained results show that our approach performs well given the low convergence period, the high level of user preferences satisfaction, and the significant decrease in energy consumption.