arXiv subjects

Ali Baheri

Publications and source records attributed to Ali Baheri.

At least 37 records · Page 2Linked to original sources

arXiv2025

Optimal Transport-Guided Safety in Temporal Difference Reinforcement Learning

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}.

cs.LG↗

arXiv2025

DEF: Diffusion-augmented Ensemble Forecasting

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.

cs.LG↗

arXiv2025

Hierarchical Neuro-Symbolic Decision Transformer

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.

cs.AI↗

arXiv2025

Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning

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.

cs.LG↗

arXiv2025

PEARL: Preconditioner Enhancement through Actor-critic Reinforcement Learning

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.

cs.LG↗

arXiv2025

Multi-Scale Conformal Prediction: A Theoretical Framework with Coverage Guarantees

We propose a multi-scale extension of conformal prediction, an approach that constructs prediction sets with finite-sample coverage guarantees under minimal statistical assumptions. Classic conformal prediction relies on a single notion of conformity, overlooking the multi-level structures that arise in applications such as image analysis, hierarchical data exploration, and multi-resolution time series modeling. In contrast, the proposed framework defines a distinct conformity function at each relevant scale or resolution, producing multiple conformal predictors whose prediction sets are then intersected to form the final multi-scale output. We establish theoretical results confirming that the multi-scale prediction set retains the marginal coverage guarantees of the original conformal framework and can, in fact, yield smaller or more precise sets in practice. By distributing the total miscoverage probability across scales in proportion to their informative power, the method further refines the set sizes. We also show that dependence between scales can lead to conservative coverage, ensuring that the actual coverage exceeds the nominal level. Numerical experiments in a synthetic classification setting demonstrate that multi-scale conformal prediction achieves or surpasses the nominal coverage level while generating smaller prediction sets compared to single-scale conformal methods.

math.ST↗

arXiv2025

SMTL: A Stratified Logic for Expressive Multi-Level Temporal Specifications

We present Stratified Metric Temporal Logic (SMTL), a novel formalism for specifying and verifying properties of complex cyber-physical systems that exhibit behaviors across multiple temporal and abstraction scales. SMTL extends existing temporal logics by incorporating a stratification operator, enabling the association of temporal properties with specific abstraction levels. This allows for the natural expression of multi-scale requirements while maintaining formal reasoning about inter-level relationships. We formalize the syntax and semantics of SMTL, proving that it strictly subsumes metric temporal logic (MTL) and offers enhanced expressiveness by capturing properties unattainable in existing logics. Numerical simulations comparing agents operating under MTL and SMTL specifications show that SMTL enhances agent coordination and safety, reducing collision rates without substantial computational overhead or compromising path efficiency. These findings underscore SMTL's potential as a valuable tool for designing and verifying complex multi-agent systems operating across diverse temporal and abstraction scales.

eess.SY↗

arXiv2024

Hierarchical Upper Confidence Bounds for Constrained Online Learning

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.

cs.LG↗

arXiv2024

Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approach

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.

eess.SY↗

arXiv2024

Optimal Transport-Assisted Risk-Sensitive Q-Learning

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.

cs.LG↗

arXiv2024

A Survey on Reinforcement Learning in Aviation Applications

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.

eess.SY↗

arXiv2024

Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning

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.

eess.SY↗

arXiv2024

BEACON: A Bayesian Evolutionary Approach for Counterexample Generation of Control Systems

The rigorous safety verification of control systems in critical applications is essential, given their increasing complexity and integration into everyday life. Simulation-based falsification approaches play a pivotal role in the safety verification of control systems, particularly within critical applications. These methods systematically explore the operational space of systems to identify configurations that result in violations of safety specifications. However, the effectiveness of traditional simulation-based falsification is frequently limited by the high dimensionality of the search space and the substantial computational resources required for exhaustive exploration. This paper presents BEACON, a novel framework that enhances the falsification process through a combination of Bayesian optimization and covariance matrix adaptation evolutionary strategy. By exploiting quantitative metrics to evaluate how closely a system adheres to safety specifications, BEACON advances the state-of-the-art in testing methodologies. It employs a model-based test point selection approach, designed to facilitate exploration across dynamically evolving search zones to efficiently uncover safety violations. Our findings demonstrate that BEACON not only locates a higher percentage of counterexamples compared to standalone BO but also achieves this with significantly fewer simulations than required by CMA-ES, highlighting its potential to optimize the verification process of control systems. This framework offers a promising direction for achieving thorough and resource-efficient safety evaluations, ensuring the reliability of control systems in critical applications.

eess.SY↗

arXiv2024

The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning

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.

cs.MA↗

arXiv2023

LLMs-augmented Contextual Bandit

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.

cs.LG↗

arXiv2023

Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning

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.

cs.LG↗

arXiv2023

Risk-Aware Reinforcement Learning through Optimal Transport Theory

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.

cs.LG↗

arXiv2023

Towards Theoretical Understanding of Data-Driven Policy Refinement

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.

cs.LG↗