Srinivas Shakkottai

Vishnu Teja Kunde, Vicram Rajagopalan, Chandra Shekhara Kaushik Valmeekam et al.

Pre-trained transformers exhibit the capability of adapting to new tasks through in-context learning (ICL), where they efficiently utilize a limited set of prompts without explicit model optimization. The canonical communication problem of estimating transmitted symbols from received observations can be modeled as an in-context learning problem: received observations are a noisy function of transmitted symbols, and this function can be represented by an unknown parameter whose statistics depend on an unknown latent context. This problem, which we term in-context estimation (ICE), has significantly greater complexity than the extensively studied linear regression problem. The optimal solution to the ICE problem is a non-linear function of the underlying context. In this paper, we prove that, for a subclass of such problems, a single-layer softmax attention transformer (SAT) computes the optimal solution of the above estimation problem in the limit of large prompt length. We also prove that the optimal configuration of such a transformer is indeed the minimizer of the corresponding training loss. Further, we empirically demonstrate the proficiency of multi-layer transformers in efficiently solving broader in-context estimation problems. Through extensive simulations, we show that solving ICE problems using transformers significantly outperforms standard approaches. Moreover, just with a few context examples, it achieves the same performance as an estimator with perfect knowledge of the latent context. The code is available \href{https://github.com/vishnutez/in-context-estimation}{here}.

Le Xie, Tong Huang, Xiangtian Zheng et al.

The transition towards carbon-neutral electricity is one of the biggest game changers in addressing climate change since it addresses the dual challenges of removing carbon emissions from the two largest sectors of emitters: electricity and transportation. The transition to a carbon-neutral electric grid poses significant challenges to conventional paradigms of modern grid planning and operation. Much of the challenge arises from the scale of the decision making and the uncertainty associated with the energy supply and demand. Artificial Intelligence (AI) could potentially have a transformative impact on accelerating the speed and scale of carbon-neutral transition, as many decision making processes in the power grid can be cast as classic, though challenging, machine learning tasks. We point out that to amplify AI's impact on carbon-neutral transition of the electric energy systems, the AI algorithms originally developed for other applications should be tailored in three layers of technology, markets, and policy.

Rayan El Helou, Kiyeob Lee, Dongqi Wu et al.

This paper presents OpenGridGym, an open-source Python-based package that allows for seamless integration of distribution market simulation with state-of-the-art artificial intelligence (AI) decision-making algorithms. We present the architecture and design choice for the proposed framework, elaborate on how users interact with OpenGridGym, and highlight its value by providing multiple cases to demonstrate its use. Four modules are used in any simulation: (1) the physical grid, (2) market mechanisms, (3) a set of trainable agents which interact with the former two modules, and (4) environment module that connects and coordinates the above three. We provide templates for each of those four, but they are easily interchangeable with custom alternatives. Several case studies are presented to illustrate the capability and potential of this toolkit in helping researchers address key design and operational questions in distribution electricity markets.

Ali Mamaghani, Ushasi Ghosh, Srinivas Shakkottai et al.

Modern wireless applications demand testing environments that capture the full complexity of next-generation (NextG) cellular networks. While digital twins promise realistic emulation, existing solutions often compromise on physical-layer fidelity and scalability or depend on specialized hardware. We present Tiny-Twin, a CPU-Native, full-stack digital twin framework that enables realistic, repeatable 5G experimentation on commodity CPUs. Tiny-Twin integrates time-varying multi-tap convolution with a complete 5G protocol stack, supporting plug-and-play replay of diverse channel traces. Through a redesigned software architecture and system-level optimizations, Tiny-Twin supports fine-grained convolution entirely in software. With built-in real-time RIC integration and per User Equipment(UE) channel isolation, it facilitates rigorous testing of network algorithms and protocol designs. Our evaluation shows that Tiny-Twin scales to multiple concurrent UEs while preserving protocol timing and end-to-end behavior, delivering a practical middle ground between low-fidelity simulators and high-cost hardware emulators. We release Tiny-Twin as an open-source platform to enable accessible, high-fidelity experimentation for NextG cellular research.

Chandra Shekhara Kaushik Valmeekam, Krishna Narayanan, Dileep Kalathil et al.

We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smaller than currently available estimates in \cite{cover1978convergent}, \cite{lutati2023focus}. A natural byproduct is an algorithm for lossless compression of English text which combines the prediction from the large language model with a lossless compression scheme. Preliminary results from limited experiments suggest that our scheme outperforms state-of-the-art text compression schemes such as BSC, ZPAQ, and paq8h.

Aria HasanzadeZonuzy, Sina Arefizadeh, Alireza Talebpour et al.

Connected automated vehicles (CAVs) could potentially be coordinated to safely attain the maximum traffic flow on roadways under dynamic traffic patterns, such as those engendered by the merger of two strings of vehicles due a lane drop. Strings of vehicles have to be shaped correctly in terms of the inter-vehicular time-gap and velocity to ensure that such operation is feasible. However, controllers that can achieve such traffic shaping over the multiple dimensions of target time-gap and velocity over a region of space are unknown. The objective of this work is to design such a controller, and to show that we can design candidate time-gap and velocity profiles such that it can stabilize the string of vehicles in attaining the target profiles. Our analysis is based on studying the system in the spacial rather than the time domain, which enables us to study stability as in terms of minimizing errors from the target profile and across vehicles as a function of location. Finally, we conduct numeral simulations in the context of shaping two platoons for merger, which we use to illustrate how to select time-gap and velocity profiles for maximizing flow and maintaining safety.

Desik Rengarajan, Sapana Chaudhary, Jaewon Kim et al.

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able to perform near-optimally on a new, related task. However, a major challenge to adopting this approach to solve real-world problems is that they are often associated with sparse reward functions that only indicate whether a task is completed partially or fully. We consider the situation where some data, possibly generated by a sub-optimal agent, is available for each task. We then develop a class of algorithms entitled Enhanced Meta-RL using Demonstrations (EMRLD) that exploit this information even if sub-optimal to obtain guidance during training. We show how EMRLD jointly utilizes RL and supervised learning over the offline data to generate a meta-policy that demonstrates monotone performance improvements. We also develop a warm started variant called EMRLD-WS that is particularly efficient for sub-optimal demonstration data. Finally, we show that our EMRLD algorithms significantly outperform existing approaches in a variety of sparse reward environments, including that of a mobile robot.

Sina Arefizadeh, Aria Hasanzadezonuzy, Alireza Talebpour et al.

The speed limit changes frequently throughout the transportation network, due to either safety (e.g., change in geometry) or congestion management (e.g., speed harmonization systems). Any abrupt reduction in the speed limit can create a shockwave that propagates upstream in traffic. Dealing with such an abrupt reduction in speed limit is particularly important while designing control laws for a platoon of automated vehicles from both stability and efficiency perspectives. This paper focuses on Adaptive Cruise Control (ACC) based platooning under a constant spacing policy, and investigates the possibility of designing a controller that ensures stability, while tracking a given target velocity profile that changes as a function of location. An ideal controller should maintain a constant spacing between successive vehicles, while tracking the desired velocity profile. The analytical investigations of this paper suggest that such a controller does not exist.

Bhavya Sai Nukapotula, Rishabh Tripathi, Seth Pregler et al.

Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant overhead, consuming up to 25\% of spectrum resources in 5G networks due to frequent pilot transmissions at sub-millisecond intervals. Recent approaches aim to reduce this burden by reconstructing CSI from spatiotemporal RF measurements, such as signal strength and direction-of-arrival. While effective in offline settings, these methods often suffer from inference latencies in the 5--100~ms range, making them impractical for real-time systems. We present GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels, the first algorithm to break the 1 ms latency barrier while maintaining high accuracy. GSpaRC represents the RF environment using a compact set of 3D Gaussian primitives, each parameterized by a lightweight neural model augmented with physics-informed features such as distance-based attenuation. Unlike traditional vision-based splatting pipelines, GSpaRC is tailored for RF reception: it employs an equirectangular projection onto a hemispherical surface centered at the receiver to reflect omnidirectional antenna behavior. A custom CUDA pipeline enables fully parallelized directional sorting, splatting, and rendering across frequency and spatial dimensions. Evaluated on multiple RF datasets, GSpaRC achieves similar CSI reconstruction fidelity to recent state-of-the-art methods while reducing training and inference time by over an order of magnitude. By trading modest GPU computation for a substantial reduction in pilot overhead, GSpaRC enables scalable, low-latency channel estimation suitable for deployment in 5G and future wireless systems. The code is available here: \href{https://github.com/Nbhavyasai/GSpaRC-WirelessGaussianSplatting.git}{GSpaRC}.

Desik Rengarajan, Nitin Ragothaman, Dileep Kalathil et al.

We consider the problem of federated offline reinforcement learning (RL), a scenario under which distributed learning agents must collaboratively learn a high-quality control policy only using small pre-collected datasets generated according to different unknown behavior policies. Naïvely combining a standard offline RL approach with a standard federated learning approach to solve this problem can lead to poorly performing policies. In response, we develop the Federated Ensemble-Directed Offline Reinforcement Learning Algorithm (FEDORA), which distills the collective wisdom of the clients using an ensemble learning approach. We develop the FEDORA codebase to utilize distributed compute resources on a federated learning platform. We show that FEDORA significantly outperforms other approaches, including offline RL over the combined data pool, in various complex continuous control environments and real-world datasets. Finally, we demonstrate the performance of FEDORA in the real-world on a mobile robot. We provide our code and a video of our experiments at \url{https://github.com/DesikRengarajan/FEDORA}.

Jeremy Carleton, Prathik Vijaykumar, Divyanshu Saxena et al.

We address the challenge of zeroth-order online convex optimization where the objective function's gradient exhibits sparsity, indicating that only a small number of dimensions possess non-zero gradients. Our aim is to leverage this sparsity to obtain useful estimates of the objective function's gradient even when the only information available is a limited number of function samples. Our motivation stems from the optimization of large-scale queueing networks that process time-sensitive jobs. Here, a job must be processed by potentially many queues in sequence to produce an output, and the service time at any queue is a function of the resources allocated to that queue. Since resources are costly, the end-to-end latency for jobs must be balanced with the overall cost of the resources used. While the number of queues is substantial, the latency function primarily reacts to resource changes in only a few, rendering the gradient sparse. We tackle this problem by introducing the Compressive Online Gradient Optimization framework which allows compressive sensing methods previously applied to stochastic optimization to achieve regret bounds with an optimal dependence on the time horizon without the full problem dimension appearing in the bound. For specific algorithms, we reduce the samples required per gradient estimate to scale with the gradient's sparsity factor rather than its full dimensionality. Numerical simulations and real-world microservices benchmarks demonstrate CONGO's superiority over gradient descent approaches that do not account for sparsity.

Sapana Chaudhary, Ujwal Dinesha, Dileep Kalathil et al.

We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-averse principles into LLM fine-tuning to minimize the occurrence of harmful outputs, particularly rare but significant events. By optimizing the risk measure of Conditional Value at Risk (CVaR), our methodology trains LLMs to exhibit superior performance in avoiding toxic outputs while maintaining effectiveness in generative tasks. Empirical evaluations on sentiment modification and toxicity mitigation tasks demonstrate the efficacy of risk-averse reinforcement learning with human feedback (RLHF) in promoting a safer and more constructive online discourse environment.

Lulin Liu, Dayou Li, Yiqing Liang et al.

Large foundation models have made significant advances in embodied intelligence, enabling synthesis and reasoning over egocentric input for household tasks. However, VLM-based auto-labeling is often noisy because the primary data sources lack accurate human action labels, chain-of-thought (CoT), and spatial annotations; these errors are amplified during long-horizon spatial instruction following. These issues stem from insufficient coverage of minute-long, daily household planning tasks and from inaccurate spatial grounding. As a result, VLM reasoning chains and world-model synthesis can hallucinate objects, skip steps, or fail to respect real-world physical attributes. To address these gaps, we introduce EgoTL. EgoTL builds a think-aloud capture pipeline for egocentric data. It uses a say-before-act protocol to record step-by-step goals and spoken reasoning with word-level timestamps, then calibrates physical properties with metric-scale spatial estimators, a memory-bank walkthrough for scene context, and clip-level tags for navigation instructions and detailed manipulation actions. With EgoTL, we are able to benchmark VLMs and World Models on six task dimensions from three layers and long-horizon generation over minute-long sequences across over 100 daily household tasks. We find that foundation models still fall short as egocentric assistants or open-world simulators. Finally, we finetune foundation models with human CoT aligned with metric labels on the training split of EgoTL, which improves long-horizon planning and reasoning, step-wise reasoning, instruction following, and spatial grounding.

Jeremy Carleton, Debajoy Mukherjee, Srinivas Shakkottai et al.

Large Language Models (LLMs) are increasingly deployed across diverse applications that demand balancing multiple, often conflicting, objectives -- such as helpfulness, harmlessness, or humor. Aligning outputs to user-specific preferences in such multi-objective settings typically requires fine-tuning models for each objective or preference configuration, which is computationally expensive and inflexible. We introduce MAVIS -- Multi-Objective Alignment via Value-Guided Inference-Time Search -- a lightweight inference-time alignment framework that enables dynamic control over LLM behavior without modifying the base model's weights. MAVIS trains a set of small value models, each corresponding to a distinct objective. At inference time, these value models are combined using user-specified weights to produce a tilting function that adjusts the base model's output distribution toward desired trade-offs. The value models are trained using a simple iterative algorithm that ensures monotonic improvement of the KL-regularized policy. We show empirically that MAVIS outperforms baselines that fine-tune per-objective models and combine them post hoc, and even approaches the performance of the idealized setting where models are fine-tuned for a user's exact preferences.

Sarat Chandra Bobbili, Ujwal Dinesha, Dheeraj Narasimha et al.

Inference-time alignment enables large language models (LLMs) to generate outputs aligned with end-user preferences without further training. Recent post-training methods achieve this by using small guidance models to modify token generation during inference. These methods typically optimize a reward function KL-regularized by the original LLM taken as the reference policy. A critical limitation, however, is their dependence on a pre-trained reward model, which requires fitting to human preference feedback--a potentially unstable process. In contrast, we introduce PITA, a novel framework that integrates preference feedback directly into the LLM's token generation, eliminating the need for a reward model. PITA learns a small preference-based guidance policy to modify token probabilities at inference time without LLM fine-tuning, reducing computational cost and bypassing the pre-trained reward model dependency. The problem is framed as identifying an underlying preference distribution, solved through stochastic search and iterative refinement of the preference-based guidance model. We evaluate PITA across diverse tasks, including mathematical reasoning and sentiment classification, demonstrating its effectiveness in aligning LLM outputs with user preferences.

Archana Bura, Sarat Chandra Bobbili, Shreyas Rameshkumar et al.

Media streaming is the dominant application over wireless edge (access) networks. The increasing softwarization of such networks has led to efforts at intelligent control, wherein application-specific actions may be dynamically taken to enhance the user experience. The goal of this work is to develop and demonstrate learning-based policies for optimal decision making to determine which clients to dynamically prioritize in a video streaming setting. We formulate the policy design question as a constrained Markov decision problem (CMDP), and observe that by using a Lagrangian relaxation we can decompose it into single-client problems. Further, the optimal policy takes a threshold form in the video buffer length, which enables us to design an efficient constrained reinforcement learning (CRL) algorithm to learn it. Specifically, we show that a natural policy gradient (NPG) based algorithm that is derived using the structure of our problem converges to the globally optimal policy. We then develop a simulation environment for training, and a real-world intelligent controller attached to a WiFi access point for evaluation. We empirically show that the structured learning approach enables fast learning. Furthermore, such a structured policy can be easily deployed due to low computational complexity, leading to policy execution taking only about 15$μ$s. Using YouTube streaming experiments in a resource constrained scenario, we demonstrate that the CRL approach can increase quality of experience (QOE) by over 30\%.

Desik Rengarajan, Gargi Vaidya, Akshay Sarvesh et al.

A major challenge in real-world reinforcement learning (RL) is the sparsity of reward feedback. Often, what is available is an intuitive but sparse reward function that only indicates whether the task is completed partially or fully. However, the lack of carefully designed, fine grain feedback implies that most existing RL algorithms fail to learn an acceptable policy in a reasonable time frame. This is because of the large number of exploration actions that the policy has to perform before it gets any useful feedback that it can learn from. In this work, we address this challenging problem by developing an algorithm that exploits the offline demonstration data generated by a sub-optimal behavior policy for faster and efficient online RL in such sparse reward settings. The proposed algorithm, which we call the Learning Online with Guidance Offline (LOGO) algorithm, merges a policy improvement step with an additional policy guidance step by using the offline demonstration data. The key idea is that by obtaining guidance from - not imitating - the offline data, LOGO orients its policy in the manner of the sub-optimal policy, while yet being able to learn beyond and approach optimality. We provide a theoretical analysis of our algorithm, and provide a lower bound on the performance improvement in each learning episode. We also extend our algorithm to the even more challenging incomplete observation setting, where the demonstration data contains only a censored version of the true state observation. We demonstrate the superior performance of our algorithm over state-of-the-art approaches on a number of benchmark environments with sparse rewards and censored state. Further, we demonstrate the value of our approach via implementing LOGO on a mobile robot for trajectory tracking and obstacle avoidance, where it shows excellent performance.

Archana Bura, Aria HasanzadeZonuzy, Dileep Kalathil et al.

Safe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations. We formulate this safe reinforcement learning (RL) problem using the framework of a finite-horizon Constrained Markov Decision Process (CMDP) with an unknown transition probability function, where we model the safety requirements as constraints on the expected cumulative costs that must be satisfied during all episodes of learning. We propose a model-based safe RL algorithm that we call Doubly Optimistic and Pessimistic Exploration (DOPE), and show that it achieves an objective regret $\tilde{O}(|\mathcal{S}|\sqrt{|\mathcal{A}| K})$ without violating the safety constraints during learning, where $|\mathcal{S}|$ is the number of states, $|\mathcal{A}|$ is the number of actions, and $K$ is the number of learning episodes. Our key idea is to combine a reward bonus for exploration (optimism) with a conservative constraint (pessimism), in addition to the standard optimistic model-based exploration. DOPE is not only able to improve the objective regret bound, but also shows a significant empirical performance improvement as compared to earlier optimism-pessimism approaches.

Khaled Nakhleh, Santosh Ganji, Ping-Chun Hsieh et al.

Whittle index policy is a powerful tool to obtain asymptotically optimal solutions for the notoriously intractable problem of restless bandits. However, finding the Whittle indices remains a difficult problem for many practical restless bandits with convoluted transition kernels. This paper proposes NeurWIN, a neural Whittle index network that seeks to learn the Whittle indices for any restless bandits by leveraging mathematical properties of the Whittle indices. We show that a neural network that produces the Whittle index is also one that produces the optimal control for a set of Markov decision problems. This property motivates using deep reinforcement learning for the training of NeurWIN. We demonstrate the utility of NeurWIN by evaluating its performance for three recently studied restless bandit problems. Our experiment results show that the performance of NeurWIN is significantly better than other RL algorithms.

Aria HasanzadeZonuzy, Archana Bura, Dileep Kalathil et al.

Many physical systems have underlying safety considerations that require that the policy employed ensures the satisfaction of a set of constraints. The analytical formulation usually takes the form of a Constrained Markov Decision Process (CMDP). We focus on the case where the CMDP is unknown, and RL algorithms obtain samples to discover the model and compute an optimal constrained policy. Our goal is to characterize the relationship between safety constraints and the number of samples needed to ensure a desired level of accuracy -- both objective maximization and constraint satisfaction -- in a PAC sense. We explore two classes of RL algorithms, namely, (i) a generative model based approach, wherein samples are taken initially to estimate a model, and (ii) an online approach, wherein the model is updated as samples are obtained. Our main finding is that compared to the best known bounds of the unconstrained regime, the sample complexity of constrained RL algorithms are increased by a factor that is logarithmic in the number of constraints, which suggests that the approach may be easily utilized in real systems.

Kiyeob Lee, Desik Rengarajan, Dileep Kalathil et al.

Mean Field Games (MFG) are the class of games with a very large number of agents and the standard equilibrium concept is a Mean Field Equilibrium (MFE). Algorithms for learning MFE in dynamic MFGs are unknown in general. Our focus is on an important subclass that possess a monotonicity property called Strategic Complementarities (MFG-SC). We introduce a natural refinement to the equilibrium concept that we call Trembling-Hand-Perfect MFE (T-MFE), which allows agents to employ a measure of randomization while accounting for the impact of such randomization on their payoffs. We propose a simple algorithm for computing T-MFE under a known model. We also introduce a model-free and a model-based approach to learning T-MFE and provide sample complexities of both algorithms. We also develop a fully online learning scheme that obviates the need for a simulator. Finally, we empirically evaluate the performance of the proposed algorithms via examples motivated by real-world applications.

Rajarshi Bhattacharyya, Archana Bura, Desik Rengarajan et al.

The predominant use of wireless access networks is for media streaming applications, which are only gaining popularity as ever more devices become available for this purpose. However, current access networks treat all packets identically, and lack the agility to determine which clients are most in need of service at a given time. Software reconfigurability of networking devices has seen wide adoption, and this in turn implies that agile control policies can be now instantiated on access networks. The goal of this work is to design, develop and demonstrate QFlow, a learning approach to create a value chain from the application on one side, to algorithms operating over reconfigurable infrastructure on the other, so that applications are able to obtain necessary resources for optimal performance. Using YouTube video streaming as an example, we illustrate how QFlow is able to adaptively provide such resources and attain a high QoE for all clients at a wireless access point.