Search Results for author: Rahul Jain

Found 37 papers, 2 papers with code

A Case Study of Efficacy and Challenges in Practical Human-in-Loop Evaluation of NLP Systems Using Checklist

no code implementations EACL (HumEval) 2021 Shaily Bhatt, Rahul Jain, Sandipan Dandapat, Sunayana Sitaram

We conduct experiments for evaluating an offensive content detection system and use a data augmentation technique for improving the model using insights from Checklist.

Data Augmentation

Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach

no code implementations17 Oct 2023 Dengwang Tang, Rahul Jain, Botao Hao, Zheng Wen

In this paper, we study the problem of efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with.

Imitation Learning

Regret Analysis of the Posterior Sampling-based Learning Algorithm for Episodic POMDPs

no code implementations16 Oct 2023 Dengwang Tang, Rahul Jain, Ashutosh Nayyar, Pierluigi Nuzzo

We propose a Posterior Sampling-based reinforcement learning algorithm for POMDPs (PS4POMDPs), which is much simpler and more implementable compared to state-of-the-art optimism-based online learning algorithms for POMDPs.

Gender-Based Comparative Study of Type 2 Diabetes Risk Factors in Kolkata, India: A Machine Learning Approach

no code implementations15 Oct 2023 Rahul Jain, Anoushka Saha, Gourav Daga, Durba Bhattacharya, Madhura Das Gupta, Sourav Chowdhury, Suparna Roychowdhury

Type 2 diabetes mellitus represents a prevalent and widespread global health concern, necessitating a comprehensive assessment of its risk factors.

Conditional Kernel Imitation Learning for Continuous State Environments

no code implementations24 Aug 2023 Rishabh Agrawal, Nathan Dahlin, Rahul Jain, Ashutosh Nayyar

Classical methods such as behavioral cloning and inverse reinforcement learning are highly sensitive to estimation errors, a problem that is particularly acute in continuous state space problems.

Density Estimation Imitation Learning +2

Optimal Control of Logically Constrained Partially Observable and Multi-Agent Markov Decision Processes

no code implementations24 May 2023 Krishna C. Kalagarla, Dhruva Kartik, Dongming Shen, Rahul Jain, Ashutosh Nayyar, Pierluigi Nuzzo

In this paper, we first introduce an optimal control theory for partially observable Markov decision processes (POMDPs) with finite linear temporal logic constraints.

Exact and Cost-Effective Automated Transformation of Neural Network Controllers to Decision Tree Controllers

no code implementations11 Apr 2023 Kevin Chang, Nathan Dahlin, Rahul Jain, Pierluigi Nuzzo

Over the past decade, neural network (NN)-based controllers have demonstrated remarkable efficacy in a variety of decision-making tasks.

Decision Making OpenAI Gym

A Novel Point-based Algorithm for Multi-agent Control Using the Common Information Approach

1 code implementation10 Apr 2023 Dengwang Tang, Ashutosh Nayyar, Rahul Jain

The Common Information (CI) approach provides a systematic way to transform a multi-agent stochastic control problem to a single-agent partially observed Markov decision problem (POMDP) called the coordinator's POMDP.

Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale

no code implementations20 Mar 2023 Botao Hao, Rahul Jain, Dengwang Tang, Zheng Wen

We first propose an Informed Posterior Sampling-based RL (iPSRL) algorithm that uses the offline dataset, and information about the expert's behavioral policy used to generate the offline dataset.

Imitation Learning reinforcement-learning +1

Leveraging Demonstrations to Improve Online Learning: Quality Matters

no code implementations7 Feb 2023 Botao Hao, Rahul Jain, Tor Lattimore, Benjamin Van Roy, Zheng Wen

This offers insight into how pretraining can greatly improve online performance and how the degree of improvement increases with the expert's competence level.

Thompson Sampling

Average-Constrained Policy Optimization

no code implementations2 Feb 2023 Akhil Agnihotri, Rahul Jain, Haipeng Luo

In this paper, we introduce a new policy optimization with function approximation algorithm for constrained MDPs with the average criterion.

Reinforcement Learning (RL)

Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation

no code implementations27 Jan 2023 Krishna C Kalagarla, Rahul Jain, Pierluigi Nuzzo

Constrained Markov decision processes (CMDPs) model scenarios of sequential decision making with multiple objectives that are increasingly important in many applications.

Decision Making

Learning Neuro-symbolic Programs for Language Guided Robot Manipulation

no code implementations12 Nov 2022 Namasivayam Kalithasan, Himanshu Singh, Vishal Bindal, Arnav Tuli, Vishwajeet Agrawal, Rahul Jain, Parag Singla, Rohan Paul

Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot.

Robot Manipulation

Optimal Communication and Control Strategies for a Multi-Agent System in the Presence of an Adversary

no code implementations8 Sep 2022 Dhruva Kartik, Sagar Sudhakara, Rahul Jain, Ashutosh Nayyar

We consider a multi-agent system in which a decentralized team of agents controls a stochastic system in the presence of an adversary.

Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints

no code implementations31 Jan 2022 Liyu Chen, Rahul Jain, Haipeng Luo

We study regret minimization for infinite-horizon average-reward Markov Decision Processes (MDPs) under cost constraints.

Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications

no code implementations27 Sep 2021 Krishna C. Kalagarla, Rahul Jain, Pierluigi Nuzzo

We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL) specification.

Motion Planning reinforcement-learning +1

A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent

no code implementations8 Sep 2021 Mehdi Jafarnia-Jahromi, Rahul Jain, Ashutosh Nayyar

In this paper, we propose Posterior Sampling Reinforcement Learning for Zero-sum Stochastic Games (PSRL-ZSG), the first online learning algorithm that achieves Bayesian regret bound of $O(HS\sqrt{AT})$ in the infinite-horizon zero-sum stochastic games with average-reward criterion.

Reinforcement Learning (RL)

Online Learning for Cooperative Multi-Player Multi-Armed Bandits

no code implementations7 Sep 2021 William Chang, Mehdi Jafarnia-Jahromi, Rahul Jain

For the first setting, we propose a UCB-inspired algorithm that achieves $O(\log T)$ regret whether the rewards are IID or Markovian.

Multi-Armed Bandits

Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path

no code implementations NeurIPS 2021 Liyu Chen, Mehdi Jafarnia-Jahromi, Rahul Jain, Haipeng Luo

We introduce a generic template for developing regret minimization algorithms in the Stochastic Shortest Path (SSP) model, which achieves minimax optimal regret as long as certain properties are ensured.

Online Learning for Stochastic Shortest Path Model via Posterior Sampling

no code implementations9 Jun 2021 Mehdi Jafarnia-Jahromi, Liyu Chen, Rahul Jain, Haipeng Luo

We consider the problem of online reinforcement learning for the Stochastic Shortest Path (SSP) problem modeled as an unknown MDP with an absorbing state.

reinforcement-learning Reinforcement Learning (RL)

Online Learning for Unknown Partially Observable MDPs

no code implementations25 Feb 2021 Mehdi Jafarnia-Jahromi, Rahul Jain, Ashutosh Nayyar

Learning optimal controllers for POMDPs when the model is unknown is harder.

Space-Efficient Algorithms for Reachability in Geometric Graphs

no code implementations13 Jan 2021 Sujoy Bhore, Rahul Jain

We show that for every $\epsilon> 0$, there exists a polynomial-time algorithm that can solve Reachability in an $n$ vertex directed penny graph, using $O(n^{1/4+\epsilon})$ space.

Computational Complexity Computational Geometry

Synthesis of Discounted-Reward Optimal Policies for Markov Decision Processes Under Linear Temporal Logic Specifications

no code implementations1 Nov 2020 Krishna C. Kalagarla, Rahul Jain, Pierluigi Nuzzo

We present a method to find an optimal policy with respect to a reward function for a discounted Markov decision process under general linear temporal logic (LTL) specifications.

Motion Planning

A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints

no code implementations23 Sep 2020 Krishna C. Kalagarla, Rahul Jain, Pierluigi Nuzzo

Constrained Markov Decision Processes (CMDPs) formalize sequential decision-making problems whose objective is to minimize a cost function while satisfying constraints on various cost functions.

Decision Making

Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

no code implementations23 Jul 2020 Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Rahul Jain

We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation.

A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret

no code implementations8 Jun 2020 Mehdi Jafarnia-Jahromi, Chen-Yu Wei, Rahul Jain, Haipeng Luo

Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function approximation.

Q-Learning reinforcement-learning +1

Randomized Policy Learning for Continuous State and Action MDPs

no code implementations8 Jun 2020 Hiteshi Sharma, Rahul Jain

The key to success has been the use of deep neural networks used to approximate the policy and value function.

Reinforcement Learning (RL)

Scheduling Flexible Non-Preemptive Loads in Smart-Grid Networks

no code implementations30 Mar 2020 Nathan Dahlin, Rahul Jain

A market consisting of a generator with thermal and renewable generation capability, a set of non-preemptive loads (i. e., loads which cannot be interrupted once started), and an independent system operator (ISO) is considered.

Scheduling

Probabilistic Contraction Analysis of Iterated Random Operators

no code implementations4 Apr 2018 Abhishek Gupta, Rahul Jain, Peter Glynn

In many branches of engineering, Banach contraction mapping theorem is employed to establish the convergence of certain deterministic algorithms.

On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits

no code implementations4 May 2015 Naumaan Nayyar, Dileep Kalathil, Rahul Jain

The objective is to design a policy that maximizes the expected reward over a time horizon for a single player setting and the sum of expected rewards for the multiplayer setting.

Multi-Armed Bandits

Empirical Q-Value Iteration

no code implementations30 Nov 2014 Dileep Kalathil, Vivek S. Borkar, Rahul Jain

We propose a new simple and natural algorithm for learning the optimal Q-value function of a discounted-cost Markov Decision Process (MDP) when the transition kernels are unknown.

Q-Learning

Approachability in Stackelberg Stochastic Games with Vector Costs

no code implementations3 Nov 2014 Dileep Kalathil, Vivek Borkar, Rahul Jain

Firstly, we give a simple and computationally tractable strategy for approachability for Stackelberg stochastic games along the lines of Blackwell's.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.