Ali Baheri

Ali Baheri, David Millard, Alireza Vahid

Distributed systems require fusing heterogeneous local probability distributions into a global summary over sparse and unreliable communication networks. Traditional consensus algorithms, which average distributions in Euclidean space, ignore their inherent geometric structure, leading to misleading results. Wasserstein barycenters offer a geometry-aware alternative by minimizing optimal transport costs, but their entropic approximations via the Sinkhorn algorithm typically require centralized coordination. This paper proposes a fully decentralized Sinkhorn algorithm that reformulates the centralized geometric mean as an arithmetic average in the log-domain, enabling approximation through local gossip protocols. Agents exchange log-messages with neighbors, interleaving consensus phases with local updates to mimic centralized iterations without a coordinator. To optimize bandwidth, we integrate event-triggered transmissions and b-bit quantization, providing tunable trade-offs between accuracy and communication while accommodating asynchrony and packet loss. Under mild assumptions, we prove convergence to a neighborhood of the centralized entropic barycenter, with bias linearly dependent on consensus tolerance, trigger threshold, and quantization error. Complexity scales near-linearly with network size. Simulations confirm near-centralized accuracy with significantly fewer messages, across various topologies and conditions.

Pouria Razzaghi, Amin Tabrizian, Wei Guo et al.

Compared with model-based control and optimization methods, reinforcement learning (RL) provides a data-driven, learning-based framework to formulate and solve sequential decision-making problems. The RL framework has become promising due to largely improved data availability and computing power in the aviation industry. Many aviation-based applications can be formulated or treated as sequential decision-making problems. Some of them are offline planning problems, while others need to be solved online and are safety-critical. In this survey paper, we first describe standard RL formulations and solutions. Then we survey the landscape of existing RL-based applications in aviation. Finally, we summarize the paper, identify the technical gaps, and suggest future directions of RL research in aviation.

Zahra Shahrooei, Mykel J. Kochenderfer, Ali Baheri

Testing controllers in safety-critical systems is vital for ensuring their safety and preventing failures. In this paper, we address the falsification problem within learning-based closed-loop control systems through simulation. This problem involves the identification of counterexamples that violate system safety requirements and can be formulated as an optimization task based on these requirements. Using full-fidelity simulator data in this optimization problem can be computationally expensive. To improve efficiency, we propose a multi-fidelity Bayesian optimization falsification framework that harnesses simulators with varying levels of accuracy. Our proposed framework can transition between different simulators and establish meaningful relationships between them. Through multi-fidelity Bayesian optimization, we determine both the optimal system input likely to be a counterexample and the appropriate fidelity level for assessment. We evaluated our approach across various Gym environments, each featuring different levels of fidelity. Our experiments demonstrate that multi-fidelity Bayesian optimization is more computationally efficient than full-fidelity Bayesian optimization and other baseline methods in detecting counterexamples. A Python implementation of the algorithm is available at https://github.com/SAILRIT/MFBO_Falsification.

Zahra Shahrooei, Mykel J. Kochenderfer, Ali Baheri

Simulation-based falsification is a practical testing method to increase confidence that the system will meet safety requirements. Because full-fidelity simulations can be computationally demanding, we investigate the use of simulators with different levels of fidelity. As a first step, we express the overall safety specification in terms of environmental parameters and structure this safety specification as an optimization problem. We propose a multi-fidelity falsification framework using Bayesian optimization, which is able to determine at which level of fidelity we should conduct a safety evaluation in addition to finding possible instances from the environment that cause the system to fail. This method allows us to automatically switch between inexpensive, inaccurate information from a low-fidelity simulator and expensive, accurate information from a high-fidelity simulator in a cost-effective way. Our experiments on various environments in simulation demonstrate that multi-fidelity Bayesian optimization has falsification performance comparable to single-fidelity Bayesian optimization but with much lower cost.

Ali Baheri, Cecilia O. Alm

Contextual bandits have emerged as a cornerstone in reinforcement learning, enabling systems to make decisions with partial feedback. However, as contexts grow in complexity, traditional bandit algorithms can face challenges in adequately capturing and utilizing such contexts. In this paper, we propose a novel integration of large language models (LLMs) with the contextual bandit framework. By leveraging LLMs as an encoder, we enrich the representation of the context, providing the bandit with a denser and more informative view. Preliminary results on synthetic datasets demonstrate the potential of this approach, showing notable improvements in cumulative rewards and reductions in regret compared to traditional bandit algorithms. This integration not only showcases the capabilities of LLMs in reinforcement learning but also opens the door to a new era of contextually-aware decision systems.

Kyle Hayes, Michael W. Fouts, Ali Baheri et al.

A promising approach for scalable Gaussian processes (GPs) is the Karhunen-Loève (KL) decomposition, in which the GP kernel is represented by a set of basis functions which are the eigenfunctions of the kernel operator. Such decomposed kernels have the potential to be very fast, and do not depend on the selection of a reduced set of inducing points. However KL decompositions lead to high dimensionality, and variable selection becomes paramount. This paper reports a new method of forward variable selection, enabled by the ordered nature of the basis functions in the KL expansion of the Bayesian Smoothing Spline ANOVA kernel (BSS-ANOVA), coupled with fast Gibbs sampling in a fully Bayesian approach. It quickly and effectively limits the number of terms, yielding a method with competitive accuracies, training and inference times for tabular datasets of low feature set dimensionality. The inference speed and accuracy makes the method especially useful for dynamic systems identification, by modeling the dynamics in the tangent space as a static problem, then integrating the learned dynamics using a high-order scheme. The methods are demonstrated on two dynamic datasets: a `Susceptible, Infected, Recovered' (SIR) toy problem, with the transmissibility used as forcing function, along with the experimental `Cascaded Tanks' benchmark dataset. Comparisons on the static prediction of time derivatives are made with a random forest (RF), a residual neural network (ResNet), and the Orthogonal Additive Kernel (OAK) inducing points scalable GP, while for the timeseries prediction comparisons are made with LSTM and GRU recurrent neural networks (RNNs) along with the SINDy package.

Ali Baheri, Hao Ren, Benjamin Johnson et al.

We present a safety verification framework for design-time and run-time assurance of learning-based components in aviation systems. Our proposed framework integrates two novel methodologies. From the design-time assurance perspective, we propose offline mixed-fidelity verification tools that incorporate knowledge from different levels of granularity in simulated environments. From the run-time assurance perspective, we propose reachability- and statistics-based online monitoring and safety guards for a learning-based decision-making model to complement the offline verification methods. This framework is designed to be loosely coupled among modules, allowing the individual modules to be developed using independent methodologies and techniques, under varying circumstances and with different tool access. The proposed framework offers feasible solutions for meeting system safety requirements at different stages throughout the system development and deployment cycle, enabling the continuous learning and assessment of the system product.

Ali Baheri

In inverse reinforcement learning (IRL), the central objective is to infer underlying reward functions from observed expert behaviors in a way that not only explains the given data but also generalizes to unseen scenarios. This ensures robustness against reward ambiguity where multiple reward functions can equally explain the same expert behaviors. While significant efforts have been made in addressing this issue, current methods often face challenges with high-dimensional problems and lack a geometric foundation. This paper harnesses the optimal transport (OT) theory to provide a fresh perspective on these challenges. By utilizing the Wasserstein distance from OT, we establish a geometric framework that allows for quantifying reward ambiguity and identifying a central representation or centroid of reward functions. These insights pave the way for robust IRL methodologies anchored in geometric interpretations, offering a structured approach to tackle reward ambiguity in high-dimensional settings.

Ali Baheri

In the dynamic and uncertain environments where reinforcement learning (RL) operates, risk management becomes a crucial factor in ensuring reliable decision-making. Traditional RL approaches, while effective in reward optimization, often overlook the landscape of potential risks. In response, this paper pioneers the integration of Optimal Transport (OT) theory with RL to create a risk-aware framework. Our approach modifies the objective function, ensuring that the resulting policy not only maximizes expected rewards but also respects risk constraints dictated by OT distances between state visitation distributions and the desired risk profiles. By leveraging the mathematical precision of OT, we offer a formulation that elevates risk considerations alongside conventional RL objectives. Our contributions are substantiated with a series of theorems, mapping the relationships between risk distributions, optimal value functions, and policy behaviors. Through the lens of OT, this work illuminates a promising direction for RL, ensuring a balanced fusion of reward pursuit and risk awareness.

Lunet Yifru, Ali Baheri

In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such environments, supported by theoretical guarantees. Our approach merges a logically-constrained RL algorithm with an evolutionary algorithm to synthesize signal temporal logic (STL) specifications. The framework is underpinned by theorems that establish the convergence of our joint learning process and provide error bounds between the discovered policy and the true optimal policy. We showcased our framework in grid-world environments, successfully identifying both acceptable safety constraints and RL policies while demonstrating the effectiveness of our theorems in practice.

Marzieh Amiri Shahbazi, Ali Baheri

Conformal prediction provides distribution-free coverage guaranties for regression; yet existing methods assume Euclidean output spaces and produce prediction regions that are poorly calibrated when responses lie on Riemannian manifolds. We propose \emph{adaptive geodesic conformal prediction}, a framework that replaces Euclidean residuals with geodesic nonconformity scores and normalizes them by a cross-validated difficulty estimator to handle heteroscedastic noise. The resulting prediction regions, geodesic caps on the sphere, have position-independent area and adapt their size to local prediction difficulty, yielding substantially more uniform conditional coverage than non-adaptive alternatives. In a synthetic sphere experiment with strong heteroscedasticity and a real-world geomagnetic field forecasting task derived from IGRF-14 satellite data, the adaptive method markedly reduces conditional coverage variability and raises worst-case coverage much closer to the nominal level, while coordinate-based baselines waste a large fraction of coverage area due to chart distortion.

David Millard, Ali Baheri

In robotics and multi-agent systems, fleets of autonomous agents often operate in subtly different environments while pursuing a common high-level objective. Directly pooling their data to learn a shared reward function is typically impractical due to differences in dynamics, privacy constraints, and limited communication bandwidth. This paper introduces an optimal transport-based approach to federated inverse reinforcement learning (IRL). Each client first performs lightweight Maximum Entropy IRL locally, adhering to its computational and privacy limitations. The resulting reward functions are then fused via a Wasserstein barycenter, which considers their underlying geometric structure. We further prove that this barycentric fusion yields a more faithful global reward estimate than conventional parameter averaging methods in federated learning. Overall, this work provides a principled and communication-efficient framework for deriving a shared reward that generalizes across heterogeneous agents and environments.

Tyler Alvarez, Ali Baheri

Large language models hallucinate during multi-step reasoning, but most existing detectors operate at the trace level: they assign one confidence score to a full output, fail to localize the first error, and often require multiple sampled completions. We frame hallucination instead as a property of the hidden-state trajectory produced during a single forward pass. Correct reasoning moves through a stable manifold of locally coherent transitions; a first error appears as a localized excursion in transport cost away from this manifold. We operationalize this view with a label-conditioned teacher that builds a trace-specific contrastive PCA lens and scores each step with seven geometric transition features, and a deployable BiLSTM student distilled from the teacher that operates on raw hidden states without inference-time labels. We prove that contrastive PCA is the optimal projection for a transport-separation objective between first error and correct states, and that single-pass first error localization holds whenever the first error creates a positive transport margin over preceding correct transitions. On ProcessBench, PRM800K, HaluEval, and TruthfulQA, both models outperform entropy-based, probing-based, and attention-based baselines in-domain; the teacher transfers stably across language models and datasets, while the student collapses under shift, a gap our distillation theory predicts. These results recast step-level hallucination detection as a problem of trajectory dynamics and identify the central obstacle to deployment: preserving the contrastive transport margin under distribution shift.

David Millard, Cecilia Alm, Rashid Ali et al.

Federated reinforcement learning typically aggregates value functions or policies by parameter averaging, which emphasizes expected return and can obscure statistical multimodality and tail behavior that matter in safety-critical settings. We formalize federated distributional reinforcement learning (FedDistRL), where clients parametrize quantile value function critics and federate these networks only. We also propose TR-FedDistRL, which builds a per client, risk-aware Wasserstein barycenter over a temporal buffer. This local barycenter provides a reference region to constrain the parameter averaged critic, ensuring necessary distributional information is not averaged out during the federation process. The distributional trust region is implemented as a shrink-squash step around this reference. Under fixed-policy evaluation, the feasibility map is nonexpansive and the update is contractive in a probe-set Wasserstein metric under evaluation. Experiments on a bandit, multi-agent gridworld, and continuous highway environment show reduced mean-smearing, improved safety proxies (catastrophe/accident rate), and lower critic/policy drift versus mean-oriented and non-federated baselines.

Zahra Shahrooei, Ali Baheri

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe behavior. This paper views safety as taking actions with more predictable consequences under environment stochasticity and introduces a temporal difference algorithm that uses optimal transport theory to quantify the uncertainty associated with actions. By integrating this uncertainty score into the decision-making objective, the agent is encouraged to favor actions with more predictable outcomes. We theoretically prove that our algorithm leads to a reduction in the probability of visiting unsafe states. We evaluate the proposed algorithm on several case studies in the presence of various forms of environment uncertainty. The results demonstrate that our method not only provides safer behavior but also maintains the performance. A Python implementation of our algorithm is available at \href{https://github.com/SAILRIT/Risk-averse-TD-Learning}{https://github.com/SAILRIT/OT-guided-TD-Learning}.

Ali Baheri, David Millard, Ignacio Laguna Peralta

Fourier Neural Operators (FNOs) can greatly accelerate PDE simulation, but they are often used without formal guarantees that they preserve basic physical structure. We show that, once the trained weights and grid are fixed, the spectral convolution in an FNO is a linear map. As a result, the full forward pass is piecewise-linear and can be represented exactly in Z3's linear real arithmetic. We study two encodings. The exact encoding compiles the spectral convolution into a dense matrix multiplication, which is sound for both proofs and counterexamples. The lighter frozen encoding replaces the spectral path with a constant, making it faster but approximate. On 10 small FNO surrogates for 1D advection-diffusion-reaction (85 to 117 parameters, grids 8 to 32), the exact encoding gives 2 sound positivity proofs on linear (ReLU-free) models, 5 sound positivity counterexamples, and 10 sound mass-violation counterexamples; the remaining 3 positivity queries on ReLU models time out. For mass non-increase, Z3 finds worse counterexamples than both gradient-based falsification and Monte Carlo on 7 of 10 models. The frozen encoding scales to grid size 64 with sub-second positivity checks, but it no longer provides certificates for the original FNO. Overall, the results make the soundness--scalability tradeoff explicit and point to what is needed for formal verification of production-scale neural operators.

Ali Baheri

Neuro-symbolic systems aim to combine the expressive structure of symbolic logic with the flexibility of neural learning; yet, generative models typically lack mechanisms to enforce declarative constraints at generation time. We propose Logic-Guided Vector Fields (LGVF), a neuro-symbolic framework that injects symbolic knowledge, specified as differentiable relaxations of logical constraints, into flow matching generative models. LGVF couples two complementary mechanisms: (1) a training-time logic loss that penalizes constraint violations along continuous flow trajectories, with weights that emphasize correctness near the target distribution; and (2) an inference-time adjustment that steers sampling using constraint gradients, acting as a lightweight, logic-informed correction to the learned dynamics. We evaluate LGVF on three constrained generation case studies spanning linear, nonlinear, and multi-region feasibility constraints. Across all settings, LGVF reduces constraint violations by 59-82% compared to standard flow matching and achieves the lowest violation rates in each case. In the linear and ring settings, LGVF also improves distributional fidelity as measured by MMD, while in the multi-obstacle setting, we observe a satisfaction-fidelity trade-off, with improved feasibility but increased MMD. Beyond quantitative gains, LGVF yields constraint-aware vector fields exhibiting emergent obstacle-avoidance behavior, routing samples around forbidden regions without explicit path planning.

Ali Baheri, Zahra Shahrooei, Chirayu Salgarkar

We present Wasserstein Adaptive Value Estimation for Actor-Critic (WAVE), an approach to enhance stability in deep reinforcement learning through adaptive Wasserstein regularization. Our method addresses the inherent instability of actor-critic algorithms by incorporating an adaptively weighted Wasserstein regularization term into the critic's loss function. We prove that WAVE achieves $\mathcal{O}\left(\frac{1}{k}\right)$ convergence rate for the critic's mean squared error and provide theoretical guarantees for stability through Wasserstein-based regularization. Using the Sinkhorn approximation for computational efficiency, our approach automatically adjusts the regularization based on the agent's performance. Theoretical analysis and experimental results demonstrate that WAVE achieves superior performance compared to standard actor-critic methods.

Ali Baheri, Cecilia O. Alm

We present a hierarchical neuro-symbolic control framework that tightly couples a classical symbolic planner with a transformer-based policy to address long-horizon decision-making under uncertainty. At the high level, the planner assembles an interpretable sequence of operators that guarantees logical coherence with task constraints, while at the low level each operator is rendered as a sub-goal token that conditions a decision transformer to generate fine-grained actions directly from raw observations. This bidirectional interface preserves the combinatorial efficiency and explainability of symbolic reasoning without sacrificing the adaptability of deep sequence models, and it permits a principled analysis that tracks how approximation errors from both planning and execution accumulate across the hierarchy. Empirical studies in stochastic grid-world domains demonstrate that the proposed method consistently surpasses purely symbolic, purely neural and existing hierarchical baselines in both success and efficiency, highlighting its robustness for sequential tasks.

David Millard, Arielle Carr, Stéphane Gaudreault et al.

We present PEARL (Preconditioner Enhancement through Actor-critic Reinforcement Learning), a novel approach to learning matrix preconditioners. Existing preconditioners such as Jacobi, Incomplete LU, and Algebraic Multigrid methods offer problem-specific advantages but rely heavily on hyperparameter tuning. Recent advances have explored using deep neural networks to learn preconditioners, though challenges such as misbehaved objective functions and costly training procedures remain. PEARL introduces a reinforcement learning approach for learning preconditioners, specifically, a contextual bandit formulation. The framework utilizes an actor-critic model, where the actor generates the incomplete Cholesky decomposition of preconditioners, and the critic evaluates them based on reward-specific feedback. To further guide the training, we design a dual-objective function, combining updates from the critic and condition number. PEARL contributes a generalizable preconditioner learning method, dynamic sparsity exploration, and cosine schedulers for improved stability and exploratory power. We compare our approach to traditional and neural preconditioners, demonstrating improved flexibility and iterative solving speed.

Ali Baheri

The multi-armed bandit (MAB) problem is a foundational framework in sequential decision-making under uncertainty, extensively studied for its applications in areas such as clinical trials, online advertising, and resource allocation. Traditional MAB formulations, however, do not adequately capture scenarios where decisions are structured hierarchically, involve multi-level constraints, or feature context-dependent action spaces. In this paper, we introduce the hierarchical constrained bandits (HCB) framework, which extends the contextual bandit problem to incorporate hierarchical decision structures and multi-level constraints. We propose the hierarchical constrained upper confidence bound (HC-UCB) algorithm, designed to address the complexities of the HCB problem by leveraging confidence bounds within a hierarchical setting. Our theoretical analysis establishes sublinear regret bounds for HC-UCB and provides high-probability guarantees for constraint satisfaction at all hierarchical levels. Furthermore, we derive a minimax lower bound on the regret for the HCB problem, demonstrating the near-optimality of our algorithm. The results are significant for real-world applications where decision-making processes are inherently hierarchical and constrained, offering a robust and efficient solution that balances exploration and exploitation across multiple levels of decision-making.

Lunet Yifru, Ali Baheri

Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades. Yet, deploying RL policies in real-world scenarios presents the crucial challenge of ensuring safety. Traditional safe RL approaches have predominantly focused on incorporating predefined safety constraints into the policy learning process. However, this reliance on predefined safety constraints poses limitations in dynamic and unpredictable real-world settings where such constraints may not be available or sufficiently adaptable. Bridging this gap, we propose a novel approach that concurrently learns a safe RL control policy and identifies the unknown safety constraint parameters of a given environment. Initializing with a parametric signal temporal logic (pSTL) safety specification and a small initial labeled dataset, we frame the problem as a bilevel optimization task, intricately integrating constrained policy optimization, using a Lagrangian-variant of the twin delayed deep deterministic policy gradient (TD3) algorithm, with Bayesian optimization for optimizing parameters for the given pSTL safety specification. Through experimentation in comprehensive case studies, we validate the efficacy of this approach across varying forms of environmental constraints, consistently yielding safe RL policies with high returns. Furthermore, our findings indicate successful learning of STL safety constraint parameters, exhibiting a high degree of conformity with true environmental safety constraints. The performance of our model closely mirrors that of an ideal scenario that possesses complete prior knowledge of safety constraints, demonstrating its proficiency in accurately identifying environmental safety constraints and learning safe policies that adhere to those constraints.

Ali Baheri

Non-Euclidean foundation models increasingly place representations in curved spaces such as hyperbolic geometry. We show that this geometry creates a boundary-driven asymmetry that backdoor triggers can exploit. Near the boundary, small input changes appear subtle to standard input-space detectors but produce disproportionately large shifts in the model's representation space. Our analysis formalizes this effect and also reveals a limitation for defenses: methods that act by pulling points inward along the radius can suppress such triggers, but only by sacrificing useful model sensitivity in that same direction. Building on these insights, we propose a simple geometry-adaptive trigger and evaluate it across tasks and architectures. Empirically, attack success increases toward the boundary, whereas conventional detectors weaken, mirroring the theoretical trends. Together, these results surface a geometry-specific vulnerability in non-Euclidean models and offer analysis-backed guidance for designing and understanding the limits of defenses.

Shriram Karpoora Sundara Pandian, Ali Baheri

Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contaminated by adversarial poisoning, system errors, or low-quality samples, leading to degraded policy performance in standard behavioral cloning (BC) and offline RL methods. This paper introduces Density-Ratio Weighted Behavioral Cloning (Weighted BC), a robust imitation learning approach that uses a small, verified clean reference set to estimate trajectory-level density ratios via a binary discriminator. These ratios are clipped and used as weights in the BC objective to prioritize clean expert behavior while down-weighting or discarding corrupted data, without requiring knowledge of the contamination mechanism. We establish theoretical guarantees showing convergence to the clean expert policy with finite-sample bounds that are independent of the contamination rate. A comprehensive evaluation framework is established, which incorporates various poisoning protocols (reward, state, transition, and action) on continuous control benchmarks. Experiments demonstrate that Weighted BC maintains near-optimal performance even at high contamination ratios outperforming baselines such as traditional BC, batch-constrained Q-learning (BCQ) and behavior regularized actor-critic (BRAC).

Ali Baheri, Lars Lindemann

Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rollouts; MCFM instead builds the conservative-dissipative split into both the vector field and a structure preserving sampler. MCFM trains via conditional flow matching on short transitions, avoiding long rollout adjoints. In inference, a Strang-prox scheme alternates a symplectic update with a proximal metric step, ensuring discrete energy decay; an optional projection enforces strict decay when a trusted energy is available. We provide continuous and discrete time guarantees linking this parameterization and sampler to conservation, monotonic dissipation, and stable rollouts. On a controlled mechanical benchmark, MCFM yields phase portraits closer to ground truth and markedly fewer energy-increase and positive energy rate events than an equally expressive unconstrained neural flow, while matching terminal distributional fit.

David Millard, Lars Lindemann, Ali Baheri

Uncertainty quantification for neural operators remains an open problem in the infinite-dimensional setting due to the lack of finite-sample coverage guarantees over functional outputs. While conformal prediction offers finite-sample guarantees in finite-dimensional spaces, it does not directly extend to function-valued outputs. Existing approaches (Gaussian processes, Bayesian neural networks, and quantile-based operators) require strong distributional assumptions or yield conservative coverage. This work extends split conformal prediction to function spaces following a two step method. We first establish finite-sample coverage guarantees in a finite-dimensional space using a discretization map in the output function space. Then these guarantees are lifted to the function-space by considering the asymptotic convergence as the discretization is refined. To characterize the effect of resolution, we decompose the conformal radius into discretization, calibration, and misspecification components. This decomposition motivates a regression-based correction to transfer calibration across resolutions. Additionally, we propose two diagnostic metrics (conformal ensemble score and internal agreement) to quantify forecast degradation in autoregressive settings. Empirical results show that our method maintains calibrated coverage with less variation under resolution shifts and achieves better coverage in super-resolution tasks.

Zahra Shahrooei, Ali Baheri

Deep off-policy actor-critic algorithms have emerged as the leading framework for reinforcement learning in continuous control domains. However, most of these algorithms suffer from poor sample efficiency, especially in environments with sparse rewards. In this paper, we take a step towards addressing this issue by providing a principled directed exploration strategy. We propose Wasserstein Barycenter Soft Actor-Critic (WBSAC) algorithm, which benefits from a pessimistic actor for temporal difference learning and an optimistic actor to promote exploration. This is achieved by using the Wasserstein barycenter of the pessimistic and optimistic policies as the exploration policy and adjusting the degree of exploration throughout the learning process. We compare WBSAC with state-of-the-art off-policy actor-critic algorithms and show that WBSAC is more sample-efficient on MuJoCo continuous control tasks.

David Millard, Arielle Carr, Stéphane Gaudreault et al.

We present DEF (\textbf{\ul{D}}iffusion-augmented \textbf{\ul{E}}nsemble \textbf{\ul{F}}orecasting), a novel approach for generating initial condition perturbations. Modern approaches to initial condition perturbations are primarily designed for numerical weather prediction (NWP) solvers, limiting their applicability in the rapidly growing field of machine learning for weather prediction. Consequently, stochastic models in this domain are often developed on a case-by-case basis. We demonstrate that a simple conditional diffusion model can (1) generate meaningful structured perturbations, (2) be applied iteratively, and (3) utilize a guidance term to intuitivey control the level of perturbation. This method enables the transformation of any deterministic neural forecasting system into a stochastic one. With our stochastic extended systems, we show that the model accumulates less error over long-term forecasts while producing meaningful forecast distributions. We validate our approach on the 5.625$^\circ$ ERA5 reanalysis dataset, which comprises atmospheric and surface variables over a discretized global grid, spanning from the 1960s to the present. On this dataset, our method demonstrates improved predictive performance along with reasonable spread estimates.

Zahra Shahrooei, Ali Baheri

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This paper presents a risk-sensitive Q-learning algorithm that leverages optimal transport theory to enhance the agent safety. By integrating optimal transport into the Q-learning framework, our approach seeks to optimize the policy's expected return while minimizing the Wasserstein distance between the policy's stationary distribution and a predefined risk distribution, which encapsulates safety preferences from domain experts. We validate the proposed algorithm in a Gridworld environment. The results indicate that our method significantly reduces the frequency of visits to risky states and achieves faster convergence to a stable policy compared to the traditional Q-learning algorithm.

Ali Baheri, Mykel J. Kochenderfer

This paper explores the integration of optimal transport (OT) theory with multi-agent reinforcement learning (MARL). This integration uses OT to handle distributions and transportation problems to enhance the efficiency, coordination, and adaptability of MARL. There are five key areas where OT can impact MARL: (1) policy alignment, where OT's Wasserstein metric is used to align divergent agent strategies towards unified goals; (2) distributed resource management, employing OT to optimize resource allocation among agents; (3) addressing non-stationarity, using OT to adapt to dynamic environmental shifts; (4) scalable multi-agent learning, harnessing OT for decomposing large-scale learning objectives into manageable tasks; and (5) enhancing energy efficiency, applying OT principles to develop sustainable MARL systems. This paper articulates how the synergy between OT and MARL can address scalability issues, optimize resource distribution, align agent policies in cooperative environments, and ensure adaptability in dynamically changing conditions.

Ali Baheri

This paper presents an approach for data-driven policy refinement in reinforcement learning, specifically designed for safety-critical applications. Our methodology leverages the strengths of data-driven optimization and reinforcement learning to enhance policy safety and optimality through iterative refinement. Our principal contribution lies in the mathematical formulation of this data-driven policy refinement concept. This framework systematically improves reinforcement learning policies by learning from counterexamples identified during data-driven verification. Furthermore, we present a series of theorems elucidating key theoretical properties of our approach, including convergence, robustness bounds, generalization error, and resilience to model mismatch. These results not only validate the effectiveness of our methodology but also contribute to a deeper understanding of its behavior in different environments and scenarios.

Ali Baheri, Subramanya Nageshrao, H. Eric Tseng et al.

In this paper, we present a safe deep reinforcement learning system for automated driving. The proposed framework leverages merits of both rule-based and learning-based approaches for safety assurance. Our safety system consists of two modules namely handcrafted safety and dynamically-learned safety. The handcrafted safety module is a heuristic safety rule based on common driving practice that ensure a minimum relative gap to a traffic vehicle. On the other hand, the dynamically-learned safety module is a data-driven safety rule that learns safety patterns from driving data. Specifically, the dynamically-leaned safety module incorporates a model lookahead beyond the immediate reward of reinforcement learning to predict safety longer into the future. If one of the future states leads to a near-miss or collision, then a negative reward will be assigned to the reward function to avoid collision and accelerate the learning process. We demonstrate the capability of the proposed framework in a simulation environment with varying traffic density. Our results show the superior capabilities of the policy enhanced with dynamically-learned safety module.