Human crowd evacuation framework and analysis using look-ahead-based reinforcement learning algorithm

Deep reinforcement learning (RL) is achieving significant success in various applications like control, robotics, games, resource management, and scheduling. However, the important problem of emergency evacuation, which clearly could benefit from RL, has been largely unaddressed. Indeed, emergency evacuation is a complex task that is difficult to solve with RL. An emergency situation is highly dynamic, with a lot of changing variables and complex constraints that make it challenging to solve. Also, there is no standard benchmark environment available that can be used to train RL agents for evacuation. A realistic environment can be complex to design. In this article, we propose the first fire evacuation environment to train RL agents for evacuation planning. The environment is modeled as a graph capturing the building structure. It consists of realistic features like fire spread, uncertainty, and bottlenecks. The implementation of our environment is in the OpenAI gym format, to facilitate future research. We also propose a new RL approach that entails pretraining the network weights of a DQN-based agent [DQN/Double-DQN (DDQN)/Dueling-DQN] to incorporate information on the shortest path to the exit. We achieved this by using tabular <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -learning to learn the shortest path on the building model’s graph. This information is transferred to the network by deliberately overfitting it on the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula> -matrix. Then, the pretrained DQN model is trained on the fire evacuation environment to generate the optimal evacuation path under time varying conditions due to fire spread, bottlenecks, and uncertainty. We perform comparisons of the proposed approach with state-of-the-art RL algorithms like DQN, DDQN, Dueling-DQN, PPO, VPG, state-action-reward-state-action (SARSA), actor–critic method, and ACKTR. The results show that our method is able to outperform state-of-the-art models by a huge margin including the original DQN-based models. Finally, our model is tested on a large and complex real building consisting of 91 rooms, with the possibility to move to any other room, hence giving 8281 actions. In order to reduce the action space, we propose a strategy that involves one step simulation. That is, an action importance vector is added to the final output of the pretrained DQN and acts like an attention mechanism. Using this strategy, the action space is reduced by 90.1%. In this manner, the model is able to deal with large action spaces. Hence, our model achieves near optimal performance on the real world emergency environment.

Active screening is a common approach in controlling the spread of recurring infectious diseases such as tuberculosis and influenza. In this approach, health workers periodically select a subset of population for screening. However, given the limited number of health workers, only a small subset of the population can be visited in any given time period. Given the recurrent nature of the disease and rapid spreading, the goal is to minimize the number of infections over a long time horizon. Active screening can be formalized as a sequential combinatorial optimization over the network of people and their connections. The main computational challenges in this formalization arise from i) the combinatorial nature of the problem, ii) the need of sequential planning and iii) the uncertainties in the infectiousness states of the population. Previous works on active screening fail to scale to large time horizon while fully considering the future effect of current interventions. In this paper, we propose a novel reinforcement learning (RL) approach based on Deep Q-Networks (DQN), with several innovative adaptations that are designed to address the above challenges. First, we use graph convolutional networks (GCNs) to represent the Q-function that exploit the node correlations of the underlying contact network. Second, to avoid solving a combinatorial optimization problem in each time period, we decompose the node set selection as a sub-sequence of decisions, and further design a two-level RL framework that solves the problem in a hierarchical way. Finally, to speed-up the slow convergence of RL which arises from reward sparseness, we incorporate ideas from curriculum learning into our hierarchical RL approach. We evaluate our RL algorithm on several real-world networks. Results show that our RL algorithm can scale up to 10 times the problem size of state-of-the-art (the variant that considers the effect of future interventions but unscalable) in terms of planning time horizon. Meanwhile, it outperforms state-of-the-art (the variant that scales up but does not consider the effect of future interventions) by up to 33% in solution quality.

The flying sidekick traveling salesman problem with stochastic travel time: A reinforcement learning approach

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in industrial and mission-critical systems that operate in closed loops. However, if the system operating conditions change, such as when an unknown fault occurs, typical safe RL algorithms cannot adapt while retaining past knowledge. Continual RL algorithms have been proposed to address this issue. However, the impact of continual adaptation on the system’s safety is an understudied problem. In this paper, we study the intersection of safe and continual RL. First, we empirically demonstrate that a popular continual RL algorithm, elastic weight consolidation, does not satisfy safety constraints in nonlinear systems subject to varying operating conditions. Specifically, we study the MuJoCo HalfCheetah and Ant environments with velocity constraints and sudden joint loss non-stationarity. Then, we show that an agent trained using constrained policy optimization, a safe RL algorithm, experiences catastrophic forgetting in continual learning settings. With this in mind, we explore a simple reward-shaping method to ensure that elastic weight consolidation prioritizes remembering both safety and task performance for safety-constrained, nonlinear, and non-stationary systems.

This paper proposes a reinforcement learning (RL) algorithm for the security problem of state estimation of cyber-physical system (CPS) under denial-of-service (DoS) attacks. The security of CPS will inevitably decline when faced with malicious cyber attacks. In order to analyze the impact of cyber attacks on CPS performance, a Kalman filter, as an adaptive state estimation technology, is combined with an RL method to evaluate the issue of system security, where estimation performance is adopted as an evaluation criterion. Then, the transition of estimation error covariance under a DoS attack is described as a Markov decision process, and the RL algorithm could be applied to resolve the optimal countermeasures. Meanwhile, the interactive combat between defender and attacker could be regarded as a two-player zero-sum game, where the Nash equilibrium policy exists but needs to be solved. Considering the energy constraints, the action selection of both sides will be restricted by setting certain cost functions. The proposed RL approach is designed from three different perspectives, including the defender, the attacker and the interactive game of two opposite sides. In addition, the framework of Q-learning and state–action–reward–state–action (SARSA) methods are investigated separately in this paper to analyze the influence of different RL algorithms. The results show that both algorithms obtain the corresponding optimal policy and the Nash equilibrium policy of the zero-sum interactive game. Through comparative analysis of two algorithms, it is verified that the differences between Q-Learning and SARSA could be applied effectively into the secure state estimation in CPS.

Reinforcement learning for a class of continuous-time input constrained optimal control problems

P2P power trading based on reinforcement learning for nanogrid clusters

Multimedia content in 5G/6G networks makes safe, confidential, and efficient content delivery difficult. Intelligent systems that adapt to the ever‐changing network environment are needed to distribute multimedia content in these networks. Reinforcement learning (RL) can optimize multimedia content distribution based on network congestion, capacity, and user preferences. This study proposes RL‐based intelligent multimedia content distribution. RL algorithms learn from the network environment and generate optimum judgments incorporating several aspects of the suggested framework. The framework delivers multimedia material securely and privately with great quality. This study provides an intelligent multimedia content delivery architecture that uses RL approaches to solve 5G/6G content delivery problems. This research presents an RL system optimized with the double DQN algorithm having a reward of 51604.93 in 7000 episodes for efficient video file sharing on intracity buses. The RL agent balances network congestion and bandwidth by leveraging multiple sources such as bus and intersection caches and base stations, improving secure multimedia content delivery in 5G/6G networks and enhancing the passenger experience. The study confirms the system's effectiveness using reward and loss metrics and identifies potential future research directions. Future work could explore additional RL algorithms, scalability for larger networks, complex delivery scenarios, and integration with blockchain and edge computing for improved security and efficiency in multimedia content delivery.

To find the path that minimizes the time to navigate between two given points in a fluid flow is known as Zermelo's problem. Here, we investigate it by using a Reinforcement Learning (RL) approach for the case of a vessel that has a slip velocity with fixed intensity, Vs, but variable direction and navigating in a 2D turbulent sea. We show that an Actor-Critic RL algorithm is able to find quasioptimal solutions for both time-independent and chaotically evolving flow configurations. For the frozen case, we also compared the results with strategies obtained analytically from continuous Optimal Navigation (ON) protocols. We show that for our application, ON solutions are unstable for the typical duration of the navigation process and are, therefore, not useful in practice. On the other hand, RL solutions are much more robust with respect to small changes in the initial conditions and to external noise, even when Vs is much smaller than the maximum flow velocity. Furthermore, we show how the RL approach is able to take advantage of the flow properties in order to reach the target, especially when the steering speed is small.

Rail transit stations with multifloor structures have been built in many cities to intensively utilize land resources and facilitate lives of community. However, being overcrowded with passengers results in high risks during daily operation. In response, this study conducted an emergency evacuation simulation and optimization in the three-dimensional (3D) space of “complex rail transit stations” (CRTSs). The aim of the paper is to provide a methodology to determine effective emergency evacuation strategies for CRTSs. The Lianglukou Rail Transit Station in Chongqing, China, was used as a case study and the AnyLogic simulation platform employed for simulating emergency evacuations. An emergency evacuation theoretical framework was established. The emergency evacuation strategies, including evacuation routes and evacuation times, were determined based on the theoretical demonstration. Simulation and optimization of emergency evacuation in the Lianglukou station were conducted. Accordingly, four main simulation results were obtained: (1) Escalators/stairs and turnstiles are key facilities in the evacuation; (2) Effective guidance for the evacuation is necessary in the public space of the station; (3) Passenger aggregation nodes should be guided for balanced evacuation; (4) Removing metal barriers is a useful evacuation optimization measure. The proposed research method and framework can be used by other CRTSs in the establishment of emergency evacuation strategies and effective optimization strategies to promote safety of transportation system. The research findings are beneficial to passengers in helping them provide valuable emergency evacuation guidance.

Autonomous navigation at unsignalized intersections: A coupled reinforcement learning and model predictive control approach

Recent advancement on reinforcement learning (RL) algorithms shows that effective learning of parametric action- selection policies can often be achieved through direct opti- mization of a performance lower bound subject to pre-defined policy behavioral constraints. Driven by this understanding, this paper seeks to develop new policy search techniques where RL is achieved through maximizing a performance lower bound ob- tained originally based on an Expectation-Maximization method. For reliable RL, our new learning techniques must also simul- taneously guarantee constrained policy behavioral changes mea- sured through KL divergence. Two separate approaches will be pursued to tackle our constrained policy optimization problems, resulting in two new RL algorithms. The first algorithm utilizes a conjugate gradient technique and a Bayesian learning method for approximate optimization. The second algorithm focuses on minimizing a loss function derived from solving the Lagrangian for constrained policy search. Both algorithms have been experi- mentally examined on several benchmark problems provided by OpenAI GYM. The experiment results clearly demonstrate that our algorithms can be highly effective in comparison to several well-known RL algorithms.

Reinforcement learning (RL) focuses on an essential aspect of intelligent behavior – how an agent can learn to make good decisions given experience and rewards in a stochastic<br>world. Yet popular RL algorithms that have enabled exciting successes in domains with good simulators (Go, Atari, etc) still often fail to learn in other domains because they rely on<br>simple heuristics for exploration. This provides additional empirical justification for essential questions around RL, specifically around algorithms that learn in a provably efficient manner through strategic exploration in any considered domain. This thesis provides new algorithms<br>and theory that enable good performance with respect to existing theoretical frameworks for evaluating RL algorithms (specifically, probably approximately correct) and introduces new stronger evaluation criteria, that may be particularly of interest as RL is applied to more real world problems.<br>For the first line of work on probably approximately correct (PAC) RL algorithms, we introduce a series of algorithms for episodic tabular domains with substantially better PAC<br>sample complexity bounds that culminate in a new algorithm with close to minimax optimal PAC and regret bounds. Look up tables are required by most sample efficient and computationally tractable algorithms, but cannot represent many practical domains. We therefore also present a new RL algorithm that can learn a good policy in environments with high dimensional observations and hidden deterministic states; unlike predecessors, this algorithm provably<br>explores not only in a statistically but also computationally efficient manner assuming access to function classes with efficient optimization oracles. To make progress it is critical to have the right measures of success. While empirical<br>demonstrations are quite clear, we find that for theoretical properties, two of the most commonly used learning frameworks, PAC guarantees and regret guarantees, each allow undesirable algorithm behavior (e.g. ignoring new observations that could improve the policy). We present<br>a new stronger learning framework called Uniform-PAC that unifies the existing frameworks and prevents undesirable algorithm properties. One caveat of all existing learning frameworks is that for any particular episode, we do not<br>know how well the algorithm will perform. To address this, we introduce the IPOC framework that requires algorithms to provide a certificate before each episode bounding how suboptimal the current policy can be. Such certifications may be of substantial interest in high stakes scenarios when an organization may wish to track or even pause an online RL system should the potential expected performance bound drop below a required expected outcome.

Reinforcement Learning (RL) has demonstrated significant potential in fields such as robotic control, autonomous driving, and financial decision-making. However, in complex environments, RL still faces challenges in stability and convergence. This study addresses this core issue by establishing a theoretical analysis framework that combines stochastic approximation theory and Lyapunov stability theory to rigorously analyze the convergence conditions and stability bounds of various RL algorithms in complex environments. Based on the theoretical analysis, we propose an Adaptive Stable RL (ASRL) algorithm, which employs dynamic regularized policy optimization and robust value function estimation to effectively mitigate policy oscillation and training divergence. Systematic experiments conducted in OpenAI Gym, MuJoCo, and customized non-stationary environments demonstrate that ASRL significantly outperforms baseline algorithms such as PPO and SAC in terms of convergence speed, final performance, and stability. Additionally, in industrial control and robotic navigation case studies, ASRL exhibits excellent adaptability and robustness. This research not only provides theoretical support for RL in complex environments but also offers optimization guidelines for algorithm design in practical applications.

This study introduces a novel controller based on a Reinforcement Learning (RL) algorithm for real-time adaptation of the stimulation pattern during FES-cycling. Core to our approach is the introduction of an RL agent that interacts with the cycling environment and learns through trial and error how to modulate the electrical charge applied to the stimulated muscle groups according to a predefined policy and while tracking a reference cadence. Instead of a static stimulation pattern to be modified by a control law, we hypothesized that a non-stationary baseline set of parameters would better adjust the amount of injected electrical charge to the time-varying characteristics of the musculature. Overground FES-assisted cycling sessions were performed by a subject with spinal cord injury (SCI AIS-A, T8). For tracking a predefined pedaling cadence, two closed-loop control laws were simultaneously used to modulate the pulse intensity of the stimulation channels responsible for evoking the muscle contractions. First, a Proportional-Integral (PI) controller was used to control the current amplitude of the stimulation channels over an initial parameter setting with predefined pulse amplitude, width and fixed frequency parameters. In parallel, an RL algorithm with a decayed-epsilon-greedy strategy was implemented to randomly explore nine different variations of pulse amplitude and width parameters over the same stimulation setting, aiming to adjust the injected electrical charge according to a predefined policy. The performance of this global control strategy was evaluated in two different RL settings and explored in two different cycling scenarios. The participant was able to pedal overground for distances over 3.5 km, and the results evidenced the RL agent learned to modify the stimulation pattern according to the predefined policy and was simultaneously able to track a predefined pedaling cadence. Despite the simplicity of our approach and the existence of more sophisticated RL algorithms, our method can be used to reduce the time needed to define stimulation patterns. Our results suggest interesting research possibilities to be explored in the future to improve cycling performance since more efficient stimulation cost dynamics can be explored and implemented for the agent to learn.