Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design method. However, a recent comprehensive analysis of state-of-the-art continuous-time RL (CT-RL) methods, namely, adaptive dynamic programming (ADP)-based CT-RL algorithms, reveals they face significant design challenges due to their complexity, numerical conditioning, and dimensional scaling issues. Despite advanced theoretical results, existing ADP CT-RL synthesis methods are inadequate in solving even small, academic problems. The goal of this work is thus to introduce a suite of new CT-RL algorithms for control of affine nonlinear systems. Our design approach relies on two important factors. First, our methods are applicable to physical systems that can be partitioned into smaller subproblems. This constructive consideration results in reduced dimensionality and greatly improved intuitiveness of design. Second, we introduce a new excitation framework to improve persistence of excitation (PE) and numerical conditioning performance via classical input/output insights. Such a design-centric approach is the first of its kind in the ADP CT-RL community. In this paper, we progressively introduce a suite of (decentralized) excitable integral reinforcement learning (EIRL) algorithms. We provide convergence and closed-loop stability guarantees, and we demonstrate these guarantees on a significant application problem of controlling an unstable, nonminimum phase hypersonic vehicle (HSV).

In multi-timescale multi-agent reinforcement learning (MARL), agents interact across different timescales. In general, policies for time-dependent behaviors, such as those induced by multiple timescales, are non-stationary. Learning non-stationary policies is challenging and typically requires sophisticated or inefficient algorithms. Motivated by the prevalence of this control problem in real-world complex systems, we introduce a simple framework for learning non-stationary policies for multi-timescale MARL. Our approach uses available information about agent timescales to define a periodic time encoding. In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy. To learn such policies, we propose a policy gradient algorithm that parameterizes the actor and critic with phase-functioned neural networks, which provide an inductive bias for periodicity. The framework's ability to effectively learn multi-timescale policies is validated on a gridworld and building energy management environment.

The emergence of microgrids (MGs) has provided a promising solution for decarbonizing and decentralizing the power grid, mitigating the challenges posed by climate change. However, MG operations often involve considering multiple objectives that represent the interests of different stakeholders, leading to potentially complex conflicts. To tackle this issue, we propose a novel multi-objective reinforcement learning framework that explores the high-dimensional objective space and uncovers the tradeoffs between conflicting objectives. This framework leverages exogenous information and capitalizes on the data-driven nature of reinforcement learning, enabling the training of a parametric policy without the need for long-term forecasts or knowledge of the underlying uncertainty distribution. The trained policies exhibit diverse, adaptive, and coordinative behaviors with the added benefit of providing interpretable insights on the dynamics of their information use. We employ this framework on the Cornell University MG (CU-MG), which is a combined heat and power MG, to evaluate its effectiveness. The results demonstrate performance improvements in all objectives considered compared to the status quo operations and offer more flexibility in navigating complex operational tradeoffs.

Robotic Exploration has evolved rapidly in the past two decades as new and more complex techniques have been created to explore unknown regions efficiently. Exciting advancements in exploration, autonomous navigation, and sensor technology have created opportunities for robots to be utilized in new environments and for new objectives ranging from mapping of abandon mines and deep oceans to the efficient creation of indoor models for navigation and search. In this paper we present and discuss a number of examples in research literature of these recent advancements, specifically focusing on robotic exploration algorithms for unmanned vehicles.

The increasing number of Distributed Energy Resources (DERs) in the emerging Smart Grid, has created an imminent need for intelligent multiagent frameworks able to utilize these assets efficiently. In this paper, we propose a novel DER aggregation framework, encompassing a multiagent architecture and various types of mechanisms for the effective management and efficient integration of DERs in the Grid. One critical component of our architecture is the Local Flexibility Estimators (LFEs) agents, which are key for offloading the Aggregator from serious or resource-intensive responsibilities -- such as addressing privacy concerns and predicting the accuracy of DER statements regarding their offered demand response services. The proposed framework allows the formation of efficient LFE cooperatives. To this end, we developed and deployed a variety of cooperative member selection mechanisms, including (a) scoring rules, and (b) (deep) reinforcement learning. We use data from the well-known PowerTAC simulator to systematically evaluate our framework. Our experiments verify its effectiveness for incorporating heterogeneous DERs into the Grid in an efficient manner. In particular, when using the well-known probabilistic prediction accuracy-incentivizing CRPS scoring rule as a selection mechanism, our framework results in increased average payments for participants, when compared with traditional commercial aggregators.

The nuclear fuel loading pattern optimization problem belongs to the class of large-scale combinatorial optimization. It is also characterized by multiple objectives and constraints, which makes it impossible to solve explicitly. Stochastic optimization methodologies including Genetic Algorithms and Simulated Annealing are used by different nuclear utilities and vendors, but hand-designed solutions continue to be the prevalent method in the industry. To improve the state-of-the-art, Deep Reinforcement Learning (RL), in particular, Proximal Policy Optimization is leveraged. This work presents a first-of-a-kind approach to utilize deep RL to solve the loading pattern problem and could be leveraged for any engineering design optimization. This paper is also to our knowledge the first to propose a study of the behavior of several hyper-parameters that influence the RL algorithm. The algorithm is highly dependent on multiple factors such as the shape of the objective function derived for the core design that behaves as a fudge factor that affects the stability of the learning. But also, an exploration/exploitation trade-off that manifests through different parameters such as the number of loading patterns seen by the agents per episode, the number of samples collected before a policy update nsteps, and an entropy factor ent_coef that increases the randomness of the policy during training. We found that RL must be applied similarly to a Gaussian Process in which the acquisition function is replaced by a parametrized policy. Then, once an initial set of hyper-parameters is found, reducing nsteps and ent_coef until no more learning is observed will result in the highest sample efficiency robustly and stably. This resulted in an economic benefit of 535,000- 642,000 $/year/plant.

The current trend toward ever-larger models makes standard retraining procedures an ever-more expensive burden. For this reason, there is growing interest in model editing, which enables computationally inexpensive, interpretable, post-hoc model modifications. While many model editing techniques are promising, research on the properties of edited models is largely limited to evaluation of validation accuracy. The robustness of edited models is an important and yet mostly unexplored topic. In this paper, we employ recently developed techniques from the field of deep learning robustness to investigate both how model editing affects the general robustness of a model, as well as the robustness of the specific behavior targeted by the edit. We find that edits tend to reduce general robustness, but that the degree of degradation depends on the editing algorithm and layers chosen. Motivated by these observations we introduce a new model editing algorithm, 1-layer interpolation (1-LI), which uses weight-space interpolation to navigate the trade-off between editing task accuracy and general robustness.

One of the primal challenges faced by utility companies is ensuring efficient supply with minimal greenhouse gas emissions. The advent of smart meters and smart grids provide an unprecedented advantage in realizing an optimised supply of thermal energies through proactive techniques such as load forecasting. In this paper, we propose a forecasting framework for heat demand based on neural networks where the time series are encoded as scalograms equipped with the capacity of embedding exogenous variables such as weather, and holiday/non-holiday. Subsequently, CNNs are utilized to predict the heat load multi-step ahead. Finally, the proposed framework is compared with other state-of-the-art methods, such as SARIMAX and LSTM. The quantitative results from retrospective experiments show that the proposed framework consistently outperforms the state-of-the-art baseline method with real-world data acquired from Denmark. A minimal mean error of 7.54% for MAPE and 417kW for RMSE is achieved with the proposed framework in comparison to all other methods.

Uncertainty quantification is crucial for assessing the predictive ability of AI algorithms. Much research has been devoted to describing the predictive distribution (PD) $F(y|\mathbf{x})$ of a target variable $y \in \mathbb{R}$ given complex input features $\mathbf{x} \in \mathcal{X}$. However, off-the-shelf PDs (from, e.g., normalizing flows and Bayesian neural networks) often lack conditional calibration with the probability of occurrence of an event given input $\mathbf{x}$ being significantly different from the predicted probability. Current calibration methods do not fully assess and enforce conditionally calibrated PDs. Here we propose \texttt{Cal-PIT}, a method that addresses both PD diagnostics and recalibration by learning a single probability-probability map from calibration data. The key idea is to regress probability integral transform scores against $\mathbf{x}$. The estimated regression provides interpretable diagnostics of conditional coverage across the feature space. The same regression function morphs the misspecified PD to a re-calibrated PD for all $\mathbf{x}$. We benchmark our corrected prediction bands (a by-product of corrected PDs) against oracle bands and state-of-the-art predictive inference algorithms for synthetic data. We also provide results for two applications: (i) probabilistic nowcasting given sequences of satellite images, and (ii) conditional density estimation of galaxy distances given imaging data (so-called photometric redshift estimation). Our code is available as a Python package https://github.com/lee-group-cmu/Cal-PIT .

During the processes of reservoir stimulation, fluids are injected into a specific area underground. The high-pressure condition created by the fluid injection causes rocks to crack to release the built-up stress, resulting in small earthquakes called microseismic events. Detecting these events in seismic recordings and locating them back to their subsurface locations are important for understanding the subsurface conditions such as fracture networks and fluid flow pathways. This knowledge is critical for applications like carbon storage, geothermal energy extraction, and oil/gas production. Traditional approaches for microseismic event detection and location often suffer from manual intervention and/or heavy computation, while current machine learning-assisted approaches typically address detection and location separately. These limitations prevent the potential for real-time microseismic monitoring, which is crucial for scientists and engineers to make instant, informed decisions, like optimization of injection strategies. Here, we proposed a machine learning-based procedure for simultaneously detecting and locating microseismic events within a single framework, using a conventional Convolutional Neural Network and an encoder-decoder Transformer. Tests on synthetically-generated and field-collected passive seismic data illustrate the accuracy, efficiency, and potential of the proposed method, which could pave the way for real-time monitoring of microseismic events in the future.