Author name cluster

Sriram Gopalakrishnan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

2 author rows

ECAI Conference 2025 Conference Paper

On Learning Action Costs from Input Plans

Marianela Morales
Alberto Pozanco
Giuseppe Canonaco
Sriram Gopalakrishnan
Daniel Borrajo
Manuela Veloso

Most of the work on learning action models focus on learning the actions’ dynamics from input plans. This allows us to specify the valid plans of a planning task. However, very little work focuses on learning action costs, which in turn allows us to rank the different plans. In this paper we introduce a new problem: that of learning the costs of a set of actions such that a set of input plans are optimal under the resulting planning model. To solve this problem we present LACFIPk, an algorithm to learn action’s costs from unlabeled input plans. We provide theoretical and empirical results showing how LACFIPk can successfully solve this task.

Details

TMLR Journal 2025 Journal Article

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation

Vaibhav Seth
Ayan Sengupta
Arinjay Pathak
Aastha A K Verma
Natraj Raman
Sriram Gopalakrishnan
Niladri Chatterjee
Tanmoy Chakraborty

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperparameter choices, leading to instability in model performance on fine-tuning downstream tasks. This paper highlights the importance of effective parameterization in low-rank fine-tuning to reduce estimator variance and enhance the stability of final model outputs. We propose MonteCLoRA, an efficient fine-tuning technique that employs Monte Carlo estimation to learn an unbiased posterior estimation of low-rank parameters with low expected variance, stabilizing fine-tuned LLMs with only $\mathcal{O}(r)$ additional parameters, for a given rank $r$. MonteCLoRA shows significant improvements in accuracy and robustness, achieving up to $3.8$% higher accuracy and $8.6$% greater robustness than existing efficient fine-tuning methods on natural language understanding tasks with pre-trained RoBERTa-base. Furthermore, in generative tasks with pre-trained LLaMA-1-7B and LLaMA-3.2-3B-Instruct, MonteCLoRA demonstrates robust performance with $50\%$ and $62\%$ lower spreads, respectively, than the contemporary, efficient fine-tuning methods. The theoretical and empirical results presented in the paper underscore how parameterization and hyperpriors balance exploration-exploitation in the low-rank parametric space, therefore leading to more optimal and robust parameter estimation during efficient fine-tuning.

PDF Details

AAAI Conference 2024 Conference Paper

SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies

Haochen Wu
Shubham Sharma
Sunandita Patra
Sriram Gopalakrishnan

With the growing use of machine learning (ML) models in critical domains such as finance and healthcare, the need to offer recourse for those adversely affected by the decisions of ML models has become more important; individuals ought to be provided with recommendations on actions to take for improving their situation and thus receiving a favorable decision. Prior work on sequential algorithmic recourse---which recommends a series of changes---focuses on action feasibility and uses the proximity of feature changes to determine action costs. However, the uncertainties of feature changes and the risk of higher than average costs in recourse have not been considered. It is undesirable if a recourse could (with some probability) result in a worse situation from which recovery requires an extremely high cost. It is essential to incorporate risks when computing and evaluating recourse. We call the recourse computed with such risk considerations as Safe Algorithmic Recourse (SafeAR). The objective is to empower people to choose a recourse based on their risk tolerance. In this work, we discuss and show how existing recourse desiderata can fail to capture the risk of higher costs. We present a method to compute recourse policies that consider variability in cost and connect algorithmic recourse literature with risk-sensitive reinforcement learning. We also adopt measures "Value at Risk" and "Conditional Value at Risk" from the financial literature to summarize risk concisely. We apply our method to two real-world datasets and compare policies with different risk-aversion levels using risk measures and recourse desiderata (sparsity and proximity).

PDF Details DOI

AAMAS Conference 2023 Conference Paper

Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments

Tung Thai
Mudit Verma
Utkarsh Soni
Sriram Gopalakrishnan
Ming Shen
Mayank Garg
Ayush Kalani
Nakul Vaidya

Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to achieve satisfactory task performance. We sketch general methods for detecting and characterizing different types of novelties, and for building an appropriate adaptive model to accommodate them utilizing logical representations and reasoning methods in stochastic partially observable multi-agent environments. We also briefly report results from evaluations of our algorithms in the game domain of Monopoly. The results show high novelty detection and accommodation rates.

PDF

NeurIPS Conference 2023 Conference Paper

On the Constrained Time-Series Generation Problem

Andrea Coletta
Sriram Gopalakrishnan
Daniel Borrajo
Svitlana Vyetrenko

Synthetic time series are often used in practical applications to augment the historical time series dataset, amplify the occurrence of rare events and also create counterfactual scenarios. Distributional-similarity (which we refer to as realism) as well as the satisfaction of certain numerical constraints are common requirements for counterfactual time series generation. For instance, the US Federal Reserve publishes synthetic market stress scenarios given by the constrained time series for financial institutions to assess their performance in hypothetical recessions. Existing approaches for generating constrained time series usually penalize training loss to enforce constraints, and reject non-conforming samples. However, these approaches would require re-training if we change constraints, and rejection sampling can be computationally expensive, or impractical for complex constraints. In this paper, we propose a novel set of methods to tackle the constrained time series generation problem and provide efficient sampling while ensuring the realism of generated time series. In particular, we frame the problem using a constrained optimization framework and then we propose a set of generative methods including 'GuidedDiffTime', a guided diffusion model. We empirically evaluate our work on several datasets for financial and energy data, where incorporating constraints is critical. We show that our approaches outperform existing work both qualitatively and quantitatively, and that 'GuidedDiffTime' does not require re-training for new constraints, resulting in a significant carbon footprint reduction, up to 92% w. r. t. existing deep learning methods.

PDF Details

PRL Workshop 2023 Workshop Paper

pyRDDLGym: From RDDL to Gym Environments

Ayal Taitler
Michael Gimelfarb
Jihwan Jeong
Sriram Gopalakrishnan
Martin Mladenov
Xiaotian Liu
Scott Sanner

We present pyRDDLGym, a Python framework for the auto-generation of OpenAI Gym environments from RDDL declarative description. The discrete time step evolution of variables in RDDL is described by conditional probability functions, which fit naturally into the Gym step scheme. Furthermore, since RDDL is a lifted description, the modification and scaling up of environments to support multiple entities and different configurations becomes trivial rather than a tedious process prone to errors. We hope that pyRDDLGym will serve as a new wind in the reinforcement learning community by enabling easy and rapid development of benchmarks due to the unique expressive power of RDDL. By providing explicit access to the model in the RDDL description, pyRDDLGym can also facilitate research on hybrid approaches to learning from interaction while leveraging model knowledge. We present the design and built-in examples of pyRDDLGym, and the additions made to the RDDL language that were incorporated into the framework.

PDF Details

ICAPS Conference 2022 Conference Paper

Assignment and Prioritization of Tasks with Uncertain Durations for Satisfying Makespans in Decentralized Execution

Sriram Gopalakrishnan
Daniel Borrajo

Task assignment under execution uncertainty and temporal/resource constraints is a standard problem for many organizations. Existing approaches in the AI planning & scheduling and operations research literature predominantly focus on dynamic controllability, and non-preemptive execution of tasks. Such solutions are appropriate for teams of agents under tight control requirements. However, in most organizations with human teams, once tasks have been assigned, humans tend to execute their assignments without a constant central oversight (which is needed for dynamic controllability). In this paper we define a problem in which execution of tasks is distributed (without central oversight), and assumes humans can preempt their tasks when other tasks of higher priority are ready to be worked on. We present two algorithms based on Tabu search and Monte Carlo Tree Search to assign and prioritize tasks for such problems. Experimental results show the improved efficacy of these approaches for this problem setting over non-preemptive strategies.

Details

AAMAS Conference 2022 Conference Paper

Minimizing Robot Navigation Graph for Position-Based Predictability by Humans

Sriram Gopalakrishnan
Subbarao Kambhampati

When multiple humans and robots are moving in spaces like restaurants, hospitals, or banks, making the robot’s movements easy to predict can help the humans co-navigate the space with the robots. Since people would be busy with their own goals, they are not paying close attention to the prior movements, or goals of multiple robots. So predictability from the robot’s current position alone would help. With this in mind, we propose using an algorithm to lay out fixed paths for the different tasks the robots would do, such that predictability from only the current position alone is optimized, and motion costs are kept within acceptable bounds.

PDF

SoCS Conference 2020 Conference Paper

Embedding Directed Graphs in Potential Fields Using FastMap-D

Sriram Gopalakrishnan
Liron Cohen 0002
Sven Koenig
T. K. Satish Kumar

Embedding undirected graphs in a Euclidean space has many computational benefits. FastMap is an efficient embedding algorithm that facilitates a geometric interpretation of problems posed on undirected graphs. However, Euclidean distances are inherently symmetric and, thus, Euclidean embeddings cannot be used for directed graphs. In this paper, we present FastMap-D, an efficient generalization of FastMap to directed graphs. FastMap-D embeds vertices using a potential field to capture the asymmetry between the to-and-fro pairwise distances in directed graphs. FastMap-D learns a potential function to define the potential field using a machine learning module. In experiments on various kinds of directed graphs, we demonstrate the advantage of FastMap-D over other approaches.

Details

AAMAS Conference 2018 Conference Paper

Recognizing Plans by Learning Embeddings from Observed Action Distributions

Yantian Zha
Yikang Li
Sriram Gopalakrishnan
Baoxin Li
Subbarao Kambhampati

Automated video surveillance requires the recognition of agent plans from videos. One promising direction for plan recognition involves learning shallow action affinity models from plan traces. Extracting such traces from raw video involves uncertainty about the actions. One solution is to represent traces as sequences of action distributions. To use such a representation in approximate plan recognition, we need embeddings of these action distributions. To address this problem, we propose a distribution to vector (Distr2Vec) model, which learns embeddings of action distributions using KL-divergence as the loss function.

PDF