Ahmadreza Moradipari

Ahmadreza Moradipari, Mahnoosh Alizadeh

We consider a Charging Network Operator (CNO) that owns a network of Electric Vehicle (EV) public charging stations and wishes to offer a menu of differentiated service options for access to its stations. This involves designing optimal pricing and routing schemes for the setting where users cannot directly choose which station they use. Instead, they choose their priority level and energy request amount from the differentiated service menu, and then the CNO directly assigns them to a station on their path. This allows higher priority users to experience lower wait times at stations, and allows the CNO to directly manage demand, exerting a higher level of control that can be used to manage the effect of EV on the grid and control station wait times. We consider the scenarios where the CNO is a social welfare-maximizing or a profit-maximizing entity, and in both cases, design pricing-routing policies that ensure users reveal their true parameters to the CNO.

Amirhossein Afsharrad, Ahmadreza Moradipari, Sanjay Lall · stanford

Recently, bandit optimization has received significant attention in real-world safety-critical systems that involve repeated interactions with humans. While there exist various algorithms with performance guarantees in the literature, practical implementation of the algorithms has not received as much attention. This work presents a comprehensive study on the computational aspects of safe bandit algorithms, specifically safe linear bandits, by introducing a framework that leverages convex programming tools to create computationally efficient policies. In particular, we first characterize the properties of the optimal policy for safe linear bandit problem and then propose an end-to-end pipeline of safe linear bandit algorithms that only involves solving convex problems. We also numerically evaluate the performance of our proposed methods.

Ahmadreza Moradipari, Mohammad Ghavamzadeh, Mahnoosh Alizadeh

We study a collaborative multi-agent stochastic linear bandit setting, where $N$ agents that form a network communicate locally to minimize their overall regret. In this setting, each agent has its own linear bandit problem (its own reward parameter) and the goal is to select the best global action w.r.t. the average of their reward parameters. At each round, each agent proposes an action, and one action is randomly selected and played as the network action. All the agents observe the corresponding rewards of the played actions and use an accelerated consensus procedure to compute an estimate of the average of the rewards obtained by all the agents. We propose a distributed upper confidence bound (UCB) algorithm and prove a high probability bound on its $T$-round regret in which we include a linear growth of regret associated with each communication round. Our regret bound is of order $\mathcal{O}\Big(\sqrt{\frac{T}{N \log(1/|λ_2|)}}\cdot (\log T)^2\Big)$, where $λ_2$ is the second largest (in absolute value) eigenvalue of the communication matrix.

Ahmadreza Moradipari, Mohammad Ghavamzadeh, Taha Rajabzadeh et al.

In this work we investigate meta-learning (or learning-to-learn) approaches in multi-task linear stochastic bandit problems that can originate from multiple environments. Inspired by the work of [1] on meta-learning in a sequence of linear bandit problems whose parameters are sampled from a single distribution (i.e., a single environment), here we consider the feasibility of meta-learning when task parameters are drawn from a mixture distribution instead. For this problem, we propose a regularized version of the OFUL algorithm that, when trained on tasks with labeled environments, achieves low regret on a new task without requiring knowledge of the environment from which the new task originates. Specifically, our regret bound for the new algorithm captures the effect of environment misclassification and highlights the benefits over learning each task separately or meta-learning without recognition of the distinct mixture components.

Ahmadreza Moradipari, Nathaniel Tucker, Mahnoosh Alizadeh

We study the traffic patterns as well as the charging patterns of a population of cost-minimizing EV owners traveling and charging within a transportation network equipped with fast charging stations (FCSs). Specifically, we study how the charging network operator (CNO) can influence where EV users charge in order to optimize the utilization of fast charging stations. These charging decisions of private EV owners affect aggregate congestion at stations (i.e., waiting time) as well as the aggregate EV charging load across the network. In this work, we capture the resulting equilibrium wait times and electricity load through a so-called \textit{traffic and charge assignment problem} (TCAP) in a fast charging station network. Our formulation allows us to: 1) Study the expected station wait times as well as the probability distribution of aggregate charging load of EVs in a FCS network in a mobility-aware fashion (an aspect unique to our work), while accounting for heterogeneities in users' travel patterns, energy demands, and geographically variant electricity prices. 2) Analytically characterize the special threshold-based structure that determines how EV owners choose where to charge their vehicle at equilibrium, in response to the FCS's charging price structure, users' energy demands, and users' mobility patterns. 3) Provide a convex optimization problem formulation to identify the network's unique equilibrium. Furthermore, we illustrate how to induce a socially optimal charging behavior by deriving the socially optimal plug-in fees and electricity prices at the charging stations.

Mahyar Abbasian, Taha Rajabzadeh, Ahmadreza Moradipari et al.

Generative Adversarial Networks (GAN) have emerged as a formidable AI tool to generate realistic outputs based on training datasets. However, the challenge of exerting control over the generation process of GANs remains a significant hurdle. In this paper, we propose a novel methodology to address this issue by integrating a reinforcement learning (RL) agent with a latent-space GAN (l-GAN), thereby facilitating the generation of desired outputs. More specifically, we have developed an actor-critic RL agent with a meticulously designed reward policy, enabling it to acquire proficiency in navigating the latent space of the l-GAN and generating outputs based on specified tasks. To substantiate the efficacy of our approach, we have conducted a series of experiments employing the MNIST dataset, including arithmetic addition as an illustrative task. The outcomes of these experiments serve to validate our methodology. Our pioneering integration of an RL agent with a GAN model represents a novel advancement, holding great potential for enhancing generative networks in the future.

Ahmadreza Moradipari, Mohammad Pedramfar, Modjtaba Shokrian Zini et al.

In this paper, we prove the first Bayesian regret bounds for Thompson Sampling in reinforcement learning in a multitude of settings. We simplify the learning problem using a discrete set of surrogate environments, and present a refined analysis of the information ratio using posterior consistency. This leads to an upper bound of order $\widetilde{O}(H\sqrt{d_{l_1}T})$ in the time inhomogeneous reinforcement learning problem where $H$ is the episode length and $d_{l_1}$ is the Kolmogorov $l_1-$dimension of the space of environments. We then find concrete bounds of $d_{l_1}$ in a variety of settings, such as tabular, linear and finite mixtures, and discuss how how our results are either the first of their kind or improve the state-of-the-art.

Sung-Yeon Park, Can Cui, Yunsheng Ma et al.

Recent advances in multi-modal large language models (MLLMs) have demonstrated strong performance across various domains; however, their ability to comprehend driving scenes remains less proven. The complexity of driving scenarios, which includes multi-view information, poses significant challenges for existing MLLMs. In this paper, we introduce NuPlanQA-Eval, a multi-view, multi-modal evaluation benchmark for driving scene understanding. To further support generalization to multi-view driving scenarios, we also propose NuPlanQA-1M, a large-scale dataset comprising 1M real-world visual question-answering (VQA) pairs. For context-aware analysis of traffic scenes, we categorize our dataset into nine subtasks across three core skills: Road Environment Perception, Spatial Relations Recognition, and Ego-Centric Reasoning. Furthermore, we present BEV-LLM, integrating Bird's-Eye-View (BEV) features from multi-view images into MLLMs. Our evaluation results reveal key challenges that existing MLLMs face in driving scene-specific perception and spatial reasoning from ego-centric perspectives. In contrast, BEV-LLM demonstrates remarkable adaptability to this domain, outperforming other models in six of the nine subtasks. These findings highlight how BEV integration enhances multi-view MLLMs while also identifying key areas that require further refinement for effective adaptation to driving scenes. To facilitate further research, we publicly release NuPlanQA at https://github.com/sungyeonparkk/NuPlanQA.

Amirhossein Afsharrad, Amirhesam Abedsoltan, Ahmadreza Moradipari et al.

Large language models (LLMs) have recently demonstrated strong potential for autonomous vehicle motion planning by reformulating trajectory prediction as a language generation problem. However, deploying capable LLMs in resource-constrained onboard systems remains a fundamental challenge. In this paper, we study how to effectively transfer motion planning knowledge from a large teacher LLM to a smaller, more deployable student model. We build on the GPT-Driver framework, which represents driving scenes as language prompts and generates waypoint trajectories with chain-of-thought reasoning, and investigate two student training paradigms: (i) on-policy generalized knowledge distillation (GKD), which trains the student on its own self-generated outputs using dense token-level feedback from the teacher, and (ii) a dense-feedback reinforcement learning (RL) baseline that uses the teacher's log-probabilities as per-token reward signals in a policy gradient framework. Experiments on the nuScenes benchmark show that GKD substantially outperforms the RL baseline and closely approaches teacher-level performance despite a 5$\times$ reduction in model size. These results highlight the practical value of on-policy distillation as a principled and effective approach to deploying LLM-based planners in autonomous driving systems.

Dechen Gao, Hang Wang, Hanchu Zhou et al.

Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot learning approaches using IL-based pre-training followed by RL-based fine-tuning are promising, this two-step learning paradigm often suffers from instability and poor sample efficiency during the RL fine-tuning phase. In this work, we introduce IN-RIL, INterleaved Reinforcement learning and Imitation Learning, for policy fine-tuning, which periodically injects IL updates after multiple RL updates and hence can benefit from the stability of IL and the guidance of expert data for more efficient exploration throughout the entire fine-tuning process. Since IL and RL involve different optimization objectives, we develop gradient separation mechanisms to prevent destructive interference during \ABBR fine-tuning, by separating possibly conflicting gradient updates in orthogonal subspaces. Furthermore, we conduct rigorous analysis, and our findings shed light on why interleaving IL with RL stabilizes learning and improves sample-efficiency. Extensive experiments on 14 robot manipulation and locomotion tasks across 3 benchmarks, including FurnitureBench, OpenAI Gym, and Robomimic, demonstrate that \ABBR can significantly improve sample efficiency and mitigate performance collapse during online finetuning in both long- and short-horizon tasks with either sparse or dense rewards. IN-RIL, as a general plug-in compatible with various state-of-the-art RL algorithms, can significantly improve RL fine-tuning, e.g., from 12\% to 88\% with 6.3x improvement in the success rate on Robomimic Transport. Project page: https://github.com/ucd-dare/IN-RIL.

Shatadal Mishra, Ahmadreza Moradipari, Nejib Ammar

Generative driving world models rely on compact latent state representations that must be efficiently transmitted and synchronized across distributed compute and connected vehicles. We study network-efficient streaming of a discrete world model state, where a stride-16 VQ-U-Net tokenizer (codebook size 8,192) maps each 288x512 frame to an 18x32 grid of token IDs (576 tokens/frame), equivalent to 936 bytes/frame under fixed-length coding. We consider a keyframe--delta protocol under strict per-message payload budgets and packet loss, and propose a fully online, label-free algorithm that prioritizes delta updates via cosine distance in codebook embedding space and triggers keyframes adaptively using a Hamming-drift threshold. The adaptive algorithm consistently improves the rate distortion frontier over periodic keyframes at matched bitrates: at 0.024 Mb/s (200-byte budget) dynamic-only embedding distortion drops from 0.0712 to 0.0661 (7.2\%), and at 0.036 Mb/s (400-byte budget) from 0.0427 to 0.0407 (4.8\%). Under 10\% delta packet loss at 200 bytes, dynamic-only distortion is 0.0757 versus 0.0789 for a matched periodic baseline. To connect state fidelity to world model usefulness, we train a lightweight next-token predictor and evaluate perplexity conditioned on streamed receiver states: at 0.024 Mb/s, dynamic-position perplexity improves from 206.0 to 193.1 (6.3\%), and at 0.036 Mb/s from 158.9 to 155.6 (2.1\%). These results support discrete token-state streaming as a practical systems layer for bandwidth-aware synchronization and improved downstream token-dynamics utility under vehicular networking constraints.

Tiejin Chen, Ahmadreza Moradipari, Kyungtae Han et al.

Trip planning for intelligent vehicles increasingly requires selecting optimal routes rather than merely producing feasible itineraries, as interacting factors such as travel time, energy consumption, and traffic conditions directly affect plan quality. Yet existing systems are largely designed for feasibility-oriented planning, and current benchmarks provide only reference answers without ground truth, preventing objective evaluation of optimization performance. In our paper, we address these limitations with an agentic AI framework that enables dynamic refinement through an orchestration agent coordinating specialized agents for traffic, charging, and points of interest, and with the Trip-planning Optimization Problems Dataset, which supplies definitive optimal solutions and category-level task structure for fine-grained analysis. Experiments show that our system achieves 77.4\% accuracy on the TOP Benchmark, significantly outperforming single-agent and workflow-based multi-agent baselines, demonstrating the importance of orchestrated agentic reasoning for robust trip planning optimization.

Amirhossein Afsharrad, Parisa Oftadeh, Ahmadreza Moradipari et al. · stanford

In this study, we explore a collaborative multi-agent stochastic linear bandit setting involving a network of $N$ agents that communicate locally to minimize their collective regret while keeping their expected cost under a specified threshold $τ$. Each agent encounters a distinct linear bandit problem characterized by its own reward and cost parameters, i.e., local parameters. The goal of the agents is to determine the best overall action corresponding to the average of these parameters, or so-called global parameters. In each round, an agent is randomly chosen to select an action based on its current knowledge of the system. This chosen action is then executed by all agents, then they observe their individual rewards and costs. We propose a safe distributed upper confidence bound algorithm, so called \textit{MA-OPLB}, and establish a high probability bound on its $T$-round regret. MA-OPLB utilizes an accelerated consensus method, where agents can compute an estimate of the average rewards and costs across the network by communicating the proper information with their neighbors. We show that our regret bound is of order $ \mathcal{O}\left(\frac{d}{τ-c_0}\frac{\log(NT)^2}{\sqrt{N}}\sqrt{\frac{T}{\log(1/|λ_2|)}}\right)$, where $λ_2$ is the second largest (in absolute value) eigenvalue of the communication matrix, and $τ-c_0$ is the known cost gap of a feasible action. We also experimentally show the performance of our proposed algorithm in different network structures.

Sung-Yeon Park, Adam Lee, Juanwu Lu et al.

Driving scene manipulation with sensor data is emerging as a promising alternative to traditional virtual driving simulators. However, existing frameworks struggle to generate realistic scenarios efficiently due to limited editing capabilities. To address these challenges, we present SIMSplat, a predictive driving scene editor with language-aligned Gaussian splatting. As a language-controlled editor, SIMSplat enables intuitive manipulation using natural language prompts. By aligning language with Gaussian-reconstructed scenes, it further supports direct querying of road objects, allowing precise and flexible editing. Our method provides detailed object-level editing, including adding new objects and modifying the trajectories of both vehicles and pedestrians, while also incorporating predictive path refinement through multi-agent motion prediction to generate realistic interactions among all agents in the scene. Experiments on the Waymo dataset demonstrate SIMSplat's extensive editing capabilities and adaptability across a wide range of scenarios. Project page: https://sungyeonparkk.github.io/simsplat/

Amirhoseein Afsharrad, Ahmadreza Moradipari, Sanjay Lall

In many real-world applications such as recommendation systems, multiple learning agents must balance exploration and exploitation while maintaining safety guarantees to avoid catastrophic failures. We study the stochastic linear bandit problem in a multi-agent networked setting where agents must satisfy stage-wise conservative constraints. A network of $N$ agents collaboratively maximizes cumulative reward while ensuring that the expected reward at every round is no less than $(1-α)$ times that of a baseline policy. Each agent observes local rewards with unknown parameters, but the network optimizes for the global parameter (average of local parameters). Agents communicate only with immediate neighbors, and each communication round incurs additional regret. We propose MA-SCLUCB (Multi-Agent Stage-wise Conservative Linear UCB), an episodic algorithm alternating between action selection and consensus-building phases. We prove that MA-SCLUCB achieves regret $\tilde{O}\left(\frac{d}{\sqrt{N}}\sqrt{T}\cdot\frac{\log(NT)}{\sqrt{\log(1/|λ_2|)}}\right)$ with high probability, where $d$ is the dimension, $T$ is the horizon, and $|λ_2|$ is the network's second largest eigenvalue magnitude. Our analysis shows: (i) collaboration yields $\frac{1}{\sqrt{N}}$ improvement despite local communication, (ii) communication overhead grows only logarithmically for well-connected networks, and (iii) stage-wise safety adds only lower-order regret. Thus, distributed learning with safety guarantees achieves near-optimal performance in reasonably connected networks.

Elaheh Akbari, Ping He, Ahmadreza Moradipari et al.

Flow-matching generative models have emerged as a powerful paradigm for continuous data generation, achieving state-of-the-art results across domains such as images, 3D shapes, and point clouds. Despite their success, these models suffer from slow inference due to the requirement of numerous sequential sampling steps. Recent work has sought to accelerate inference by reducing the number of sampling steps. In particular, Mean Flows offer a one-step generation approach that delivers substantial speedups while retaining strong generative performance. Yet, in many continuous domains, Mean Flows fail to faithfully approximate the behavior of the original multi-step flow-matching process. In this work, we address this limitation by incorporating optimal transport-based sampling strategies into the Mean Flow framework, enabling one-step generators that better preserve the fidelity and diversity of the original multi-step flow process. Experiments on controlled low-dimensional settings and on high-dimensional tasks such as image generation, image-to-image translation, and point cloud generation demonstrate that our approach achieves superior inference accuracy in one-step generative modeling.

Ahmadreza Moradipari, Berkay Turan, Yasin Abbasi-Yadkori et al.

We study two model selection settings in stochastic linear bandits (LB). In the first setting, which we refer to as feature selection, the expected reward of the LB problem is in the linear span of at least one of $M$ feature maps (models). In the second setting, the reward parameter of the LB problem is arbitrarily selected from $M$ models represented as (possibly) overlapping balls in $\mathbb R^d$. However, the agent only has access to misspecified models, i.e.,~estimates of the centers and radii of the balls. We refer to this setting as parameter selection. For each setting, we develop and analyze a computationally efficient algorithm that is based on a reduction from bandits to full-information problems. This allows us to obtain regret bounds that are not worse (up to a $\sqrt{\log M}$ factor) than the case where the true model is known. This is the best-reported dependence on the number of models $M$ in these settings. Finally, we empirically show the effectiveness of our algorithms using synthetic and real-world experiments.

Ahmadreza Moradipari, Christos Thrampoulidis, Mahnoosh Alizadeh

We study stage-wise conservative linear stochastic bandits: an instance of bandit optimization, which accounts for (unknown) safety constraints that appear in applications such as online advertising and medical trials. At each stage, the learner must choose actions that not only maximize cumulative reward across the entire time horizon but further satisfy a linear baseline constraint that takes the form of a lower bound on the instantaneous reward. For this problem, we present two novel algorithms, stage-wise conservative linear Thompson Sampling (SCLTS) and stage-wise conservative linear UCB (SCLUCB), that respect the baseline constraints and enjoy probabilistic regret bounds of order O(\sqrt{T} \log^{3/2}T) and O(\sqrt{T} \log T), respectively. Notably, the proposed algorithms can be adjusted with only minor modifications to tackle different problem variations, such as constraints with bandit-feedback, or an unknown sequence of baseline actions. We discuss these and other improvements over the state-of-the-art. For instance, compared to existing solutions, we show that SCLTS plays the (non-optimal) baseline action at most O(\log{T}) times (compared to O(\sqrt{T})). Finally, we make connections to another studied form of safety constraints that takes the form of an upper bound on the instantaneous reward. While this incurs additional complexity to the learning process as the optimal action is not guaranteed to belong to the safe set at each round, we show that SCLUCB can properly adjust in this setting via a simple modification.

Modjtaba Shokrian Zini, Mohammad Pedramfar, Matthew Riemer et al.

Coagent networks formalize the concept of arbitrary networks of stochastic agents that collaborate to take actions in a reinforcement learning environment. Prominent examples of coagent networks in action include approaches to hierarchical reinforcement learning (HRL), such as those using options, which attempt to address the exploration exploitation trade-off by introducing abstract actions at different levels by sequencing multiple stochastic networks within the HRL agents. We first provide a unifying perspective on the many diverse examples that fall under coagent networks. We do so by formalizing the rules of execution in a coagent network, enabled by the novel and intuitive idea of execution paths in a coagent network. Motivated by parameter sharing in the hierarchical option-critic architecture, we revisit the coagent network theory and achieve a much shorter proof of the policy gradient theorem using our idea of execution paths, without any assumption on how parameters are shared among coagents. We then generalize our setting and proof to include the scenario where coagents act asynchronously. This new perspective and theorem also lead to more mathematically accurate and performant algorithms than those in the existing literature. Lastly, by running nonstationary RL experiments, we survey the performance and properties of different generalizations of option-critic models.

Ahmadreza Moradipari, Sanae Amani, Mahnoosh Alizadeh et al.

The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under additional \textit{linear safety constraints} that need to be satisfied at each round. We provide a new safe algorithm based on linear Thompson Sampling (TS) for this problem and show a frequentist regret of order $\mathcal{O} (d^{3/2}\log^{1/2}d \cdot T^{1/2}\log^{3/2}T)$, which remarkably matches the results provided by (Abeille et al., 2017) for the standard linear TS algorithm in the absence of safety constraints. We compare the performance of our algorithm with UCB-based safe algorithms and highlight how the inherently randomized nature of TS leads to a superior performance in expanding the set of safe actions the algorithm has access to at each round.

Ahmadreza Moradipari, Sina Shahsavari, Ashkan Esmaeili et al.

Inference and Estimation in Missing Information (MI) scenarios are important topics in Statistical Learning Theory and Machine Learning (ML). In ML literature, attempts have been made to enhance prediction through precise feature selection methods. In sparse linear models, LASSO is well-known in extracting the desired support of the signal and resisting against noisy systems. When sparse models are also suffering from MI, the sparse recovery and inference of the missing models are taken into account simultaneously. In this paper, we will introduce an approach which enjoys sparse regression and covariance matrix estimation to improve matrix completion accuracy, and as a result enhancing feature selection preciseness which leads to reduction in prediction Mean Squared Error (MSE). We will compare the effect of employing covariance matrix in enhancing estimation accuracy to the case it is not used in feature selection. Simulations show the improvement in the performance as compared to the case where the covariance matrix estimation is not used.