Search Results for author: Balaraman Ravindran

Found 66 papers, 22 papers with code

TAG: Task-based Accumulated Gradients for Lifelong learning

1 code implementation11 May 2021 Pranshu Malviya, Sarath Chandar, Balaraman Ravindran

We also show that our method performs better than several state-of-the-art methods in lifelong learning on complex datasets with a large number of tasks.

Neural Fitted Q Iteration based Optimal Bidding Strategy in Real Time Reactive Power Market_1

no code implementations7 Jan 2021 Jahnvi Patel, Devika Jay, Balaraman Ravindran, K. Shanti Swarup

In this paper, a pioneer work on learning optimal bidding strategies from observation and experience in a three-stage reactive power market is reported.

Stochastic Optimization

qRRT: Quality-Biased Incremental RRT for Optimal Motion Planning in Non-Holonomic Systems

no code implementations7 Jan 2021 Nahas Pareekutty, Francis James, Balaraman Ravindran, Suril V. Shah

This paper presents a sampling-based method for optimal motion planning in non-holonomic systems in the absence of known cost functions.

Motion Planning Optimal Motion Planning

Reinforcement Learning for Unified Allocation and Patrolling in Signaling Games with Uncertainty

no code implementations18 Dec 2020 Aravind Venugopal, Elizabeth Bondi, Harshavardhan Kamarthi, Keval Dholakia, Balaraman Ravindran, Milind Tambe

We therefore first propose a novel GSG model that combines defender allocation, patrolling, real-time drone notification to human patrollers, and drones sending warning signals to attackers.

Decision Making Multiagent Systems

Relational Boosted Bandits

1 code implementation16 Dec 2020 Ashutosh Kakadiya, Sriraam Natarajan, Balaraman Ravindran

Contextual bandits algorithms have become essential in real-world user interaction problems in recent years.

Link Prediction Multi-Armed Bandits

Hypergraph Partitioning using Tensor Eigenvalue Decomposition

no code implementations16 Nov 2020 Deepak Maurya, Balaraman Ravindran

We also show improvement for the min-cut solution on 2-uniform hypergraphs (graphs) over the standard spectral partitioning algorithm.

graph partitioning hypergraph partitioning

Goal directed molecule generation using Monte Carlo Tree Search

no code implementations30 Oct 2020 Anand A. Rajasekar, Karthik Raman, Balaraman Ravindran

One challenging and essential task in biochemistry is the generation of novel molecules with desired properties.

MADRaS : Multi Agent Driving Simulator

no code implementations2 Oct 2020 Anirban Santara, Sohan Rudra, Sree Aditya Buridi, Meha Kaushik, Abhishek Naik, Bharat Kaul, Balaraman Ravindran

In this work, we present MADRaS, an open-source multi-agent driving simulator for use in the design and evaluation of motion planning algorithms for autonomous driving.

Autonomous Driving Car Racing +3

Reinforcement Learning for Improving Object Detection

no code implementations18 Aug 2020 Siddharth Nayak, Balaraman Ravindran

The performance of a trained object detection neural network depends a lot on the image quality.

Object Detection

A Causal Linear Model to Quantify Edge Flow and Edge Unfairness for UnfairEdge Prioritization and Discrimination Removal

no code implementations10 Jul 2020 Pavan Ravishankar, Pranshu Malviya, Balaraman Ravindran

Unlike previous works that only make cautionary claims of discrimination and de-biases data after its generation, this paper attempts to prioritize unfair sources before mitigating their unfairness in the real-world.

On Incorporating Structural Information to improve Dialogue Response Generation

1 code implementation WS 2020 Nikita Moghe, Priyesh Vijayan, Balaraman Ravindran, Mitesh M. Khapra

This requires capturing structural, sequential and semantic information from the conversation context and the background resources.

Understanding Dynamic Scenes using Graph Convolution Networks

1 code implementation9 May 2020 Sravan Mylavarapu, Mahtab Sandhu, Priyesh Vijayan, K. Madhava Krishna, Balaraman Ravindran, Anoop Namboodiri

We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera.

Motion Segmentation Semantic Segmentation +1

Towards Transparent and Explainable Attention Models

2 code implementations ACL 2020 Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran

To make attention mechanisms more faithful and plausible, we propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse.

EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks

1 code implementation ICLR 2020 Sanchari Sen, Balaraman Ravindran, Anand Raghunathan

Our results indicate that EMPIR boosts the average adversarial accuracies by 42. 6%, 15. 2% and 10. 5% for the DNN models trained on the MNIST, CIFAR-10 and ImageNet datasets respectively, when compared to single full-precision models, without sacrificing accuracy on the unperturbed inputs.

Self-Driving Cars

SEERL: Sample Efficient Ensemble Reinforcement Learning

no code implementations15 Jan 2020 Rohan Saphal, Balaraman Ravindran, Dheevatsa Mudigere, Sasikanth Avancha, Bharat Kaul

However, ensemble methods are relatively less popular in reinforcement learning owing to the high sample complexity and computational expense involved in obtaining a diverse ensemble.

Continuous Control Ensemble Learning +1

Reinforcement Learning for Multi-Objective Optimization of Online Decisions in High-Dimensional Systems

no code implementations1 Oct 2019 Hardik Meisheri, Vinita Baniwal, Nazneen N Sultana, Balaraman Ravindran, Harshad Khadilkar

This paper describes a purely data-driven solution to a class of sequential decision-making problems with a large number of concurrent online decisions, with applications to computing systems and operations research.

Decision Making

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

no code implementations9 Sep 2019 Arjun Manoharan, Rahul Ramesh, Balaraman Ravindran

Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent.

Let's Ask Again: Refine Network for Automatic Question Generation

1 code implementation IJCNLP 2019 Preksha Nema, Akash Kumar Mohankumar, Mitesh M. Khapra, Balaji Vasan Srinivasan, Balaraman Ravindran

It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer.

Question Generation

Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling

1 code implementation8 Jul 2019 Harshavardhan Kamarthi, Priyesh Vijayan, Bryan Wilder, Balaraman Ravindran, Milind Tambe

A serious challenge when finding influential actors in real-world social networks is the lack of knowledge about the structure of the underlying network.

Graph Sampling

ExTra: Transfer-guided Exploration

no code implementations27 Jun 2019 Anirban Santara, Rishabh Madan, Balaraman Ravindran, Pabitra Mitra

Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment.

Learning Interpretable Models Using an Oracle

no code implementations17 Jun 2019 Abhishek Ghose, Balaraman Ravindran

Our solution to this problem possesses the following key favorable properties: (1) the number of optimization variables is independent of the dimensionality of the data: a fixed number of seven variables are used (2) our technique is model agnostic - in that both the interpretable model and the oracle may belong to arbitrary model families.

Sentence Embedding

MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning

no code implementations17 May 2019 Manan Tomar, Akhil Sathuluri, Balaraman Ravindran

Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion.

Successor Options: An Option Discovery Framework for Reinforcement Learning

1 code implementation14 May 2019 Rahul Ramesh, Manan Tomar, Balaraman Ravindran

This work adopts a complementary approach, where we attempt to discover options that navigate to landmark states.

Interpretability with Accurate Small Models

no code implementations4 May 2019 Abhishek Ghose, Balaraman Ravindran

Our technique identifies the training data distribution to learn from that leads to the highest accuracy for a model of a given size.

Network Representation Learning: Consolidation and Renewed Bearing

1 code implementation2 May 2019 Saket Gurukar, Priyesh Vijayan, Aakash Srinivasan, Goonmeet Bajaj, Chen Cai, Moniba Keymanesh, Saravana Kumar, Pranav Maneriker, Anasua Mitra, Vedang Patel, Balaraman Ravindran, Srinivasan Parthasarathy

An important area of research that has emerged over the last decade is the use of graphs as a vehicle for non-linear dimensionality reduction in a manner akin to previous efforts based on manifold learning with uses for downstream database processing, machine learning and visualization.

Dimensionality Reduction General Classification +3

Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning

no code implementations5 Feb 2019 Harish Kumar, Balaraman Ravindran

On top of our LSTM neural network that learnt musical sequences in this representation, we built an RL agent that learnt to find combinations of songs whose joint dominance produced pleasant compositions.

An Active Learning Framework for Efficient Robust Policy Search

no code implementations1 Jan 2019 Sai Kiran Narayanaswami, Nandan Sudarsanam, Balaraman Ravindran

We also present a Multi-Task Learning perspective to the problem of Robust Policy Search, and draw connections from our proposed framework to existing work on Multi-Task Learning.

Active Learning Continuous Control +1

Hypergraph Clustering: A Modularity Maximization Approach

no code implementations28 Dec 2018 Tarun Kumar, Sankaran Vaidyanathan, Harini Ananthapadmanabhan, Srinivasan Parthasarathy, Balaraman Ravindran

Clustering on hypergraphs has been garnering increased attention with potential applications in network analysis, VLSI design and computer vision, among others.

Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning

1 code implementation26 Dec 2018 Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.

Image Classification Object Detection +1

Discovering hierarchies using Imitation Learning from hierarchy aware policies

no code implementations1 Dec 2018 Ameet Deshpande, Harshavardhan Kamarthi, Balaraman Ravindran

Learning options that allow agents to exhibit temporally higher order behavior has proven to be useful in increasing exploration, reducing sample complexity and for various transfer scenarios.

Imitation Learning

Improvements on Hindsight Learning

no code implementations16 Sep 2018 Ameet Deshpande, Srikanth Sarma, Ashutosh Jha, Balaraman Ravindran

One such approach is Hindsight Experience replay which uses an off-policy Reinforcement Learning algorithm to learn a goal conditioned policy.

Policy Gradient Methods

Pack and Detect: Fast Object Detection in Videos Using Region-of-Interest Packing

no code implementations5 Sep 2018 Athindran Ramesh Kumar, Balaraman Ravindran, Anand Raghunathan

Based on these observations, we propose Pack and Detect (PaD), an approach to reduce the computational requirements of object detection in videos.

Object Tracking Real-Time Object Detection +2

Fusion Graph Convolutional Networks

1 code implementation31 May 2018 Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy, Balaraman Ravindran

State-of-the-art models for node classification on such attributed graphs use differentiable recursive functions that enable aggregation and filtering of neighborhood information from multiple hops.

General Classification Node Classification

HOPF: Higher Order Propagation Framework for Deep Collective Classification

1 code implementation31 May 2018 Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy, Balaraman Ravindran

Given a graph where every node has certain attributes associated with it and some nodes have labels associated with them, Collective Classification (CC) is the task of assigning labels to every unlabeled node using information from the node as well as its neighbors.

Classification General Classification

Language Expansion In Text-Based Games

no code implementations17 May 2018 Ghulam Ahmed Ansari, Sagar J P, Sarath Chandar, Balaraman Ravindran

Text-based games are suitable test-beds for designing agents that can learn by interaction with the environment in the form of natural language text.

text-based games

DiGrad: Multi-Task Reinforcement Learning with Shared Actions

no code implementations27 Feb 2018 Parijat Dewangan, S Phaniteja, K. Madhava Krishna, Abhishek Sarkar, Balaraman Ravindran

In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continuous action spaces, which we call as DiGrad (Differential Policy Gradient).

Multi-Task Learning

Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks

1 code implementation31 Jan 2018 Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inherent plasticity of deep neural networks which allows them to recover from the loss of pruned filters once the rest of the filters are fine-tuned.

Image Classification Object Detection

Rate of Change Analysis for Interestingness Measures

no code implementations14 Dec 2017 Nandan Sudarsanam, Nishanth Kumar, Abhishek Sharma, Balaraman Ravindran

We present a comprehensive analysis of 50 interestingness measures and classify them in accordance with the two properties.

General Classification

Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates

no code implementations9 Nov 2017 Subhojyoti Mukherjee, K. P. Naveen, Nandan Sudarsanam, Balaraman Ravindran

We propose a novel variant of the UCB algorithm (referred to as Efficient-UCB-Variance (EUCBV)) for minimizing cumulative regret in the stochastic multi-armed bandit (MAB) setting.

Shared Learning : Enhancing Reinforcement in $Q$-Ensembles

no code implementations14 Sep 2017 Rakesh R. Menon, Balaraman Ravindran

Deep Reinforcement Learning has been able to achieve amazing successes in a variety of domains from video games to continuous control by trying to maximize the cumulative reward.

Atari Games Continuous Control +1

RAIL: Risk-Averse Imitation Learning

1 code implementation20 Jul 2017 Anirban Santara, Abhishek Naik, Balaraman Ravindran, Dipankar Das, Dheevatsa Mudigere, Sasikanth Avancha, Bharat Kaul

Generative Adversarial Imitation Learning (GAIL) is a state-of-the-art algorithm for learning policies when the expert's behavior is available as a fixed set of trajectories.

Autonomous Driving Continuous Control +1

Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning

no code implementations ICLR 2018 Sahil Sharma, Girish Raguvir J, Srivatsan Ramesh, Balaraman Ravindran

Our second major contribution is that we propose a generalization of lambda-returns called Confidence-based Autodidactic Returns (CAR), wherein the RL agent learns the weighting of the n-step returns in an end-to-end manner.

Decision Making

Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning

no code implementations20 May 2017 Sahil Sharma, Aravind Suresh, Rahul Ramesh, Balaraman Ravindran

Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains.

Decision Making Q-Learning

Thresholding Bandits with Augmented UCB

no code implementations7 Apr 2017 Subhojyoti Mukherjee, K. P. Naveen, Nandan Sudarsanam, Balaraman Ravindran

In this paper we propose the Augmented-UCB (AugUCB) algorithm for a fixed-budget version of the thresholding bandit problem (TBP), where the objective is to identify a set of arms whose quality is above a threshold.

DyVEDeep: Dynamic Variable Effort Deep Neural Networks

no code implementations4 Apr 2017 Sanjay Ganapathy, Swagath Venkataramani, Balaraman Ravindran, Anand Raghunathan

Complementary to these approaches, DyVEDeep is a dynamic approach that exploits the heterogeneity in the inputs to DNNs to improve their compute efficiency with comparable classification accuracy.

Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning

no code implementations20 Feb 2017 Sahil Sharma, Aravind Srinivas, Balaraman Ravindran

Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it.

Car Racing Decision Making

Learning to Multi-Task by Active Sampling

1 code implementation ICLR 2018 Sahil Sharma, Ashutosh Jha, Parikshit Hegde, Balaraman Ravindran

In this work, we propose an efficient multi-task learning framework which solves multiple goal-directed tasks in an on-line setup without the need for expert supervision.

Active Learning Meta-Learning +1

Exploration for Multi-task Reinforcement Learning with Deep Generative Models

no code implementations29 Nov 2016 Sai Praveen Bangaru, JS Suhas, Balaraman Ravindran

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP.

EPOpt: Learning Robust Neural Network Policies Using Model Ensembles

no code implementations5 Oct 2016 Aravind Rajeswaran, Sarvjeet Ghotra, Balaraman Ravindran, Sergey Levine

Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks.

Domain Adaptation

Dynamic Frame skip Deep Q Network

no code implementations17 May 2016 Aravind Srinivas, Sahil Sharma, Balaraman Ravindran

Deep Reinforcement Learning methods have achieved state of the art performance in learning control policies for the games in the Atari 2600 domain.

Atari Games

Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering

no code implementations17 May 2016 Aravind Srinivas, Ramnandan Krishnamurthy, Peeyush Kumar, Balaraman Ravindran

This paper introduces an automated skill acquisition framework in reinforcement learning which involves identifying a hierarchical description of the given task in terms of abstract states and extended actions between abstract states.

Hierarchical Reinforcement Learning Video Prediction

Linear Bandit algorithms using the Bootstrap

no code implementations4 May 2016 Nandan Sudarsanam, Balaraman Ravindran

One of the proposed methods, X-Random bootstrap, performs better than the baselines in-terms of cumulative regret across various degrees of noise and different number of trials.

Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning

no code implementations NAACL 2016 Janarthanan Rajendran, Mitesh M. Khapra, Sarath Chandar, Balaraman Ravindran

In this work, we address a real-world scenario where no direct parallel data is available between two views of interest (say, $V_1$ and $V_2$) but parallel data is available between each of these views and a pivot view ($V_3$).

Document Classification Representation Learning +1

Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

2 code implementations10 Oct 2015 Janarthanan Rajendran, Aravind Srinivas, Mitesh M. Khapra, P. Prasanna, Balaraman Ravindran

Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task.

TSEB: More Efficient Thompson Sampling for Policy Learning

no code implementations10 Oct 2015 P. Prasanna, Sarath Chandar, Balaraman Ravindran

In this paper, we propose TSEB, a Thompson Sampling based algorithm with adaptive exploration bonus that aims to solve the problem with tighter PAC guarantees, while being cautious on the regret as well.

A Reinforcement Learning Approach to Online Learning of Decision Trees

no code implementations24 Jul 2015 Abhinav Garlapati, aditi raghunathan, Vaishnavh Nagarajan, Balaraman Ravindran

Online decision tree learning algorithms typically examine all features of a new data point to update model parameters.

Correlational Neural Networks

2 code implementations27 Apr 2015 Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle, Balaraman Ravindran

CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace.

Representation Learning Transfer Learning

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