This paper proposes a data-driven solution for Volt-VAR control problem in active distribution system. As distribution system models are always inaccurate and incomplete, it is quite difficult to solve the problem. To handle with this dilemma, this paper formulates the Volt-VAR control problem as a constrained Markov decision process (CMDP). By synergistically combining the augmented Lagrangian method and soft actor critic algorithm, a novel safe off-policy reinforcement learning (RL) approach is proposed in this paper to solve the CMDP. The actor network is updated in a policy gradient manner with the Lagrangian value function. A double-critics network is adopted to synchronously estimate the action-value function to avoid overestimation bias. The proposed algorithm does not require strong convexity guarantee of examined problems and is sample efficient. A two-stage strategy is adopted for offline training and online execution, so the accurate distribution system model is no longer needed. To achieve scalability, a centralized training distributed execution strategy is adopted for a multi-agent framework, which enables a decentralized Volt-VAR control for large-scale distribution system. Comprehensive numerical experiments with real-world electricity data demonstrate that our proposed algorithm can achieve high solution optimality and constraints compliance.
This paper studies the safe reinforcement learning problem formulated as an episodic finite-horizon tabular constrained Markov decision process with an unknown transition kernel and stochastic reward and cost functions. We propose a model-based algorithm based on novel cost and reward function estimators that provide tighter cost pessimism and reward optimism. While guaranteeing no constraint violation in every episode, our algorithm achieves a regret upper bound of $\widetilde{\mathcal{O}}((\bar C - \bar C_b)^{-1}H^{2.5} S\sqrt{AK})$ where $\bar C$ is the cost budget for an episode, $\bar C_b$ is the expected cost under a safe baseline policy over an episode, $H$ is the horizon, and $S$, $A$ and $K$ are the number of states, actions, and episodes, respectively. This improves upon the best-known regret upper bound, and when $\bar C- \bar C_b=\Omega(H)$, it nearly matches the regret lower bound of $\Omega(H^{1.5}\sqrt{SAK})$. We deduce our cost and reward function estimators via a Bellman-type law of total variance to obtain tight bounds on the expected sum of the variances of value function estimates. This leads to a tighter dependence on the horizon in the function estimators. We also present numerical results to demonstrate the computational effectiveness of our proposed framework.
Safe reinforcement learning (RL) is a promising approach for many real-world decision-making problems where ensuring safety is a critical necessity. In safe RL research, while expected cumulative safety constraints (ECSCs) are typically the first choices, chance constraints are often more pragmatic for incorporating safety under uncertainties. This paper proposes a \textit{flipping-based policy} for Chance-Constrained Markov Decision Processes (CCMDPs). The flipping-based policy selects the next action by tossing a potentially distorted coin between two action candidates. The probability of the flip and the two action candidates vary depending on the state. We establish a Bellman equation for CCMDPs and further prove the existence of a flipping-based policy within the optimal solution sets. Since solving the problem with joint chance constraints is challenging in practice, we then prove that joint chance constraints can be approximated into Expected Cumulative Safety Constraints (ECSCs) and that there exists a flipping-based policy in the optimal solution sets for constrained MDPs with ECSCs. As a specific instance of practical implementations, we present a framework for adapting constrained policy optimization to train a flipping-based policy. This framework can be applied to other safe RL algorithms. We demonstrate that the flipping-based policy can improve the performance of the existing safe RL algorithms under the same limits of safety constraints on Safety Gym benchmarks.
This paper proposes a safety modulator actor-critic (SMAC) method to address safety constraint and overestimation mitigation in model-free safe reinforcement learning (RL). A safety modulator is developed to satisfy safety constraints by modulating actions, allowing the policy to ignore safety constraint and focus on maximizing reward. Additionally, a distributional critic with a theoretical update rule for SMAC is proposed to mitigate the overestimation of Q-values with safety constraints. Both simulation and real-world scenarios experiments on Unmanned Aerial Vehicles (UAVs) hovering confirm that the SMAC can effectively maintain safety constraints and outperform mainstream baseline algorithms.
While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to use a shield that validates and adjusts the agent's actions to ensure compliance with a provided set of safety specifications. For real-world robotic domains, it is essential to define safety specifications over continuous state and action spaces to accurately account for system dynamics and compute new actions that minimally deviate from the agent's original decision. In this paper, we present the first shielding approach specifically designed to ensure the satisfaction of safety requirements in continuous state and action spaces, making it suitable for practical robotic applications. Our method builds upon realizability, an essential property that confirms the shield will always be able to generate a safe action for any state in the environment. We formally prove that realizability can be verified for stateful shields, enabling the incorporation of non-Markovian safety requirements, such as loop avoidance. Finally, we demonstrate the effectiveness of our approach in ensuring safety without compromising the policy's success rate by applying it to a navigation problem and a multi-agent particle environment.
The high penetration of distributed energy resources (DERs) in modern smart power systems introduces unforeseen uncertainties for the electricity sector, leading to increased complexity and difficulty in the operation and control of power systems. As a cutting-edge machine learning technology, deep reinforcement learning (DRL) has been widely implemented in recent years to handle the uncertainty in power systems. However, in critical infrastructures such as power systems, safety issues always receive top priority, while DRL may not always meet the safety requirements of power system operators. The concept of safe reinforcement learning (safe RL) is emerging as a potential solution to overcome the shortcomings of conventional DRL in the operation and control of power systems. This study provides a rigorous review of the latest research efforts focused on safe RL to derive power system control policies while accounting for the unique safety requirements of power grids. Furthermore, this study highlights various safe RL algorithms applied in diverse applications within the power system sector, from single grid-connected power converters, residential smart homes, and buildings to large power distribution networks. For all methods outlined, a discussion on their bottlenecks, research challenges, and potential opportunities in the operation and control of power system applications is also presented. This review aims to support research in the area of safe RL algorithms, embracing smart power system operation with safety constraints amid high uncertainty from DERs.
Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots. While most approaches in the Safe Reinforcement Learning area do not require prior knowledge of constraints and robot kinematics and rely solely on data, it is often difficult to deploy them in complex real-world settings. Instead, model-based approaches that incorporate prior knowledge of the constraints and dynamics into the learning framework have proven capable of deploying the learning algorithm directly on the real robot. Unfortunately, while an approximated model of the robot dynamics is often available, the safety constraints are task-specific and hard to obtain: they may be too complicated to encode analytically, too expensive to compute, or it may be difficult to envision a priori the long-term safety requirements. In this paper, we bridge this gap by extending the safe exploration method, ATACOM, with learnable constraints, with a particular focus on ensuring long-term safety and handling of uncertainty. Our approach is competitive or superior to state-of-the-art methods in final performance while maintaining safer behavior during training.
Pruning neural networks (NNs) can streamline them but risks removing vital parameters from safe reinforcement learning (RL) policies. We introduce an interpretable RL method called VERINTER, which combines NN pruning with model checking to ensure interpretable RL safety. VERINTER exactly quantifies the effects of pruning and the impact of neural connections on complex safety properties by analyzing changes in safety measurements. This method maintains safety in pruned RL policies and enhances understanding of their safety dynamics, which has proven effective in multiple RL settings.
Reinforcement learning (RL)-based methods have achieved significant success in managing grid-interactive efficient buildings (GEBs). However, RL does not carry intrinsic guarantees of constraint satisfaction, which may lead to severe safety consequences. Besides, in GEB control applications, most existing safe RL approaches rely only on the regularisation parameters in neural networks or penalty of rewards, which often encounter challenges with parameter tuning and lead to catastrophic constraint violations. To provide enforced safety guarantees in controlling GEBs, this paper designs a physics-inspired safe RL method whose decision-making is enhanced through safe interaction with the environment. Different energy resources in GEBs are optimally managed to minimize energy costs and maximize customer comfort. The proposed approach can achieve strict constraint guarantees based on prior knowledge of a set of developed hard steady-state rules. Simulations on the optimal management of GEBs, including heating, ventilation, and air conditioning (HVAC), solar photovoltaics, and energy storage systems, demonstrate the effectiveness of the proposed approach.
Safe reinforcement learning (SafeRL) extends standard reinforcement learning with the idea of safety, where safety is typically defined through the constraint of the expected cost return of a trajectory being below a set limit. However, this metric fails to distinguish how costs accrue, treating infrequent severe cost events as equal to frequent mild ones, which can lead to riskier behaviors and result in unsafe exploration. We introduce a new metric, expected maximum consecutive cost steps (EMCC), which addresses safety during training by assessing the severity of unsafe steps based on their consecutive occurrence. This metric is particularly effective for distinguishing between prolonged and occasional safety violations. We apply EMMC in both on- and off-policy algorithm for benchmarking their safe exploration capability. Finally, we validate our metric through a set of benchmarks and propose a new lightweight benchmark task, which allows fast evaluation for algorithm design.
Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications that require dexterous, reactive, and rapid skills in complex environments. These constraints, which may represent task, safety, or actuator limitations, are essential for ensuring the proper functioning of robotic platforms and preventing unexpected behaviors. Recent advances in kinodynamic planning demonstrate that learning-to-plan techniques can generate complex and reactive motions under intricate constraints. However, these techniques necessitate the analytical modeling of both the robot and the entire task, a limiting assumption when systems are extremely complex or when constructing accurate task models is prohibitive. This paper addresses this limitation by combining learning-to-plan methods with reinforcement learning, resulting in a novel integration of black-box learning of motion primitives and optimization. We evaluate our approach against state-of-the-art safe reinforcement learning methods, showing that our technique, particularly when exploiting task structure, outperforms baseline methods in challenging scenarios such as planning to hit in robot air hockey. This work demonstrates the potential of our integrated approach to enhance the performance and safety of robots operating under complex kinodynamic constraints.
Safe Reinforcement Learning (Safe RL) is one of the prevalently studied subcategories of trial-and-error-based methods with the intention to be deployed on real-world systems. In safe RL, the goal is to maximize reward performance while minimizing constraints, often achieved by setting bounds on constraint functions and utilizing the Lagrangian method. However, deploying Lagrangian-based safe RL in real-world scenarios is challenging due to the necessity of threshold fine-tuning, as imprecise adjustments may lead to suboptimal policy convergence. To mitigate this challenge, we propose a unified Lagrangian-based model-free architecture called Meta Soft Actor-Critic Lagrangian (Meta SAC-Lag). Meta SAC-Lag uses meta-gradient optimization to automatically update the safety-related hyperparameters. The proposed method is designed to address safe exploration and threshold adjustment with minimal hyperparameter tuning requirement. In our pipeline, the inner parameters are updated through the conventional formulation and the hyperparameters are adjusted using the meta-objectives which are defined based on the updated parameters. Our results show that the agent can reliably adjust the safety performance due to the relatively fast convergence rate of the safety threshold. We evaluate the performance of Meta SAC-Lag in five simulated environments against Lagrangian baselines, and the results demonstrate its capability to create synergy between parameters, yielding better or competitive results. Furthermore, we conduct a real-world experiment involving a robotic arm tasked with pouring coffee into a cup without spillage. Meta SAC-Lag is successfully trained to execute the task, while minimizing effort constraints.
Recent advancements in machine learning based energy management approaches, specifically reinforcement learning with a safety layer (OptLayerPolicy) and a metaheuristic algorithm generating a decision tree control policy (TreeC), have shown promise. However, their effectiveness has only been demonstrated in computer simulations. This paper presents the real-world validation of these methods, comparing against model predictive control and simple rule-based control benchmark. The experiments were conducted on the electrical installation of 4 reproductions of residential houses, which all have their own battery, photovoltaic and dynamic load system emulating a non-controllable electrical load and a controllable electric vehicle charger. The results show that the simple rules, TreeC, and model predictive control-based methods achieved similar costs, with a difference of only 0.6%. The reinforcement learning based method, still in its training phase, obtained a cost 25.5\% higher to the other methods. Additional simulations show that the costs can be further reduced by using a more representative training dataset for TreeC and addressing errors in the model predictive control implementation caused by its reliance on accurate data from various sources. The OptLayerPolicy safety layer allows safe online training of a reinforcement learning agent in the real-world, given an accurate constraint function formulation. The proposed safety layer method remains error-prone, nonetheless, it is found beneficial for all investigated methods. The TreeC method, which does require building a realistic simulation for training, exhibits the safest operational performance, exceeding the grid limit by only 27.1 Wh compared to 593.9 Wh for reinforcement learning.
The deployment of artificial intelligence (AI) in decision-making applications requires ensuring an appropriate level of safety and reliability, particularly in changing environments that contain a large number of unknown observations. To address this challenge, we propose a novel safe reinforcement learning (RL) approach that utilizes an anomalous state sequence to enhance RL safety. Our proposed solution Safe Reinforcement Learning with Anomalous State Sequences (AnoSeqs) consists of two stages. First, we train an agent in a non-safety-critical offline 'source' environment to collect safe state sequences. Next, we use these safe sequences to build an anomaly detection model that can detect potentially unsafe state sequences in a 'target' safety-critical environment where failures can have high costs. The estimated risk from the anomaly detection model is utilized to train a risk-averse RL policy in the target environment; this involves adjusting the reward function to penalize the agent for visiting anomalous states deemed unsafe by our anomaly model. In experiments on multiple safety-critical benchmarking environments including self-driving cars, our solution approach successfully learns safer policies and proves that sequential anomaly detection can provide an effective supervisory signal for training safety-aware RL agents
The transition to sustainable energy is a key challenge of our time, requiring modifications in the entire pipeline of energy production, storage, transmission, and consumption. At every stage, new sequential decision-making challenges emerge, ranging from the operation of wind farms to the management of electrical grids or the scheduling of electric vehicle charging stations. All such problems are well suited for reinforcement learning, the branch of machine learning that learns behavior from data. Therefore, numerous studies have explored the use of reinforcement learning for sustainable energy. This paper surveys this literature with the intention of bridging both the underlying research communities: energy and machine learning. After a brief introduction of both fields, we systematically list relevant sustainability challenges, how they can be modeled as a reinforcement learning problem, and what solution approaches currently exist in the literature. Afterwards, we zoom out and identify overarching reinforcement learning themes that appear throughout sustainability, such as multi-agent, offline, and safe reinforcement learning. Lastly, we also cover standardization of environments, which will be crucial for connecting both research fields, and highlight potential directions for future work. In summary, this survey provides an extensive overview of reinforcement learning methods for sustainable energy, which may play a vital role in the energy transition.
Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we introduce OASIS (cOnditionAl diStributIon Shaping), a new paradigm in offline safe RL designed to overcome these critical limitations. OASIS utilizes a conditional diffusion model to synthesize offline datasets, thus shaping the data distribution toward a beneficial target domain. Our approach makes compliance with safety constraints through effective data utilization and regularization techniques to benefit offline safe RL training. Comprehensive evaluations on public benchmarks and varying datasets showcase OASIS's superiority in benefiting offline safe RL agents to achieve high-reward behavior while satisfying the safety constraints, outperforming established baselines. Furthermore, OASIS exhibits high data efficiency and robustness, making it suitable for real-world applications, particularly in tasks where safety is imperative and high-quality demonstrations are scarce.
Offline Safe Reinforcement Learning (RL) seeks to address safety constraints by learning from static datasets and restricting exploration. However, these approaches heavily rely on the dataset and struggle to generalize to unseen scenarios safely. In this paper, we aim to improve safety during the deployment of vision-based robotic tasks through online fine-tuning an offline pretrained policy. To facilitate effective fine-tuning, we introduce model-based RL, which is known for its data efficiency. Specifically, our method employs in-sample optimization to improve offline training efficiency while incorporating reachability guidance to ensure safety. After obtaining an offline safe policy, a safe policy expansion approach is leveraged for online fine-tuning. The performance of our method is validated on simulation benchmarks with five vision-only tasks and through real-world robot deployment using limited data. It demonstrates that our approach significantly improves the generalization of offline policies to unseen safety-constrained scenarios. To the best of our knowledge, this is the first work to explore offline-to-online RL for safe generalization tasks.
Different classes of safe reinforcement learning algorithms have shown satisfactory performance in various types of safety requirement scenarios. However, the existing methods mainly address one or several classes of specific safety requirement scenario problems and cannot be applied to arbitrary safety requirement scenarios. In addition, the optimization objectives of existing reinforcement learning algorithms are misaligned with the task requirements. Based on the need to address these issues, we propose $\mathrm{E^{2}CFD}$, an effective and efficient cost function design framework. $\mathrm{E^{2}CFD}$ leverages the capabilities of a large language model (LLM) to comprehend various safety scenarios and generate corresponding cost functions. It incorporates the \textit{fast performance evaluation (FPE)} method to facilitate rapid and iterative updates to the generated cost function. Through this iterative process, $\mathrm{E^{2}CFD}$ aims to obtain the most suitable cost function for policy training, tailored to the specific tasks within the safety scenario. Experiments have proven that the performance of policies trained using this framework is superior to traditional safe reinforcement learning algorithms and policies trained with carefully designed cost functions.
The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches, particularly reinforcement learning (RL), have shown significant promise in addressing complex control challenges in power systems, because RL can learn from interactive feedback without needing prior knowledge of the system model. However, the training process of model-free RL methods relies heavily on random decisions for exploration, which may result in ``bad" decisions that violate critical safety constraints and lead to catastrophic control outcomes. Due to the inability of RL methods to theoretically ensure decision safety in power systems, directly deploying traditional RL algorithms in the real world is deemed unacceptable. Consequently, the safety issue in RL applications, known as safe RL, has garnered considerable attention in recent years, leading to numerous important developments. This paper provides a comprehensive review of the state-of-the-art safe RL techniques and discusses how these techniques can be applied to power system control problems such as frequency regulation, voltage control, and energy management. We then present discussions on key challenges and future research directions, related to convergence and optimality, training efficiency, universality, and real-world deployment.
Given the availability of more comprehensive measurement data in modern power systems, reinforcement learning (RL) has gained significant interest in operation and control. Conventional RL relies on trial-and-error interactions with the environment and reward feedback, which often leads to exploring unsafe operating regions and executing unsafe actions, especially when deployed in real-world power systems. To address these challenges, safe RL has been proposed to optimize operational objectives while ensuring safety constraints are met, keeping actions and states within safe regions throughout both training and deployment. Rather than relying solely on manually designed penalty terms for unsafe actions, as is common in conventional RL, safe RL methods reviewed here primarily leverage advanced and proactive mechanisms. These include techniques such as Lagrangian relaxation, safety layers, and theoretical guarantees like Lyapunov functions to rigorously enforce safety boundaries. This paper provides a comprehensive review of safe RL methods and their applications across various power system operations and control domains, including security control, real-time operation, operational planning, and emerging areas. It summarizes existing safe RL techniques, evaluates their performance, analyzes suitable deployment scenarios, and examines algorithm benchmarks and application environments. The paper also highlights real-world implementation cases and identifies critical challenges such as scalability in large-scale systems and robustness under uncertainty, providing potential solutions and outlining future directions to advance the reliable integration and deployment of safe RL in modern power systems.