326 citations · 1k across the 67 of their papers we have counts for
41 papers · 1 filter
MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learning
Aravind Venugopal, Stephanie Milani, Fei Fang +1
Multi-agent reinforcement learning (MARL) methods often suffer from high sample complexity, limiting their use in real-world problems where data is sparse or expensive to collect.…
Physics-Informed Model-Based Reinforcement Learning
Adithya Ramesh, Balaraman Ravindran
We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample…
Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning
Kushal Chauhan, Soumya Chatterjee, Akash Reddy +2
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstract…
A Causal Approach for Unfair Edge Prioritization and Discrimination Removal
Pavan Ravishankar, Pranshu Malviya, Balaraman Ravindran
In budget-constrained settings aimed at mitigating unfairness, like law enforcement, it is essential to prioritize the sources of unfairness before taking measures to mitigate them…
Smooth Imitation Learning via Smooth Costs and Smooth Policies
Sapana Chaudhary, Balaraman Ravindran
Imitation learning (IL) is a popular approach in the continuous control setting as among other reasons it circumvents the problems of reward mis-specification and exploration in re…
Semi-Supervised Deep Learning for Multiplex Networks
Anasua Mitra, Priyesh Vijayan, Ranbir Sanasam +3
Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer.…
Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes
Siddharth Nishtala, Lovish Madaan, Aditya Mate +11
India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100,000 live births. Lack of access to preventive care information is a major contributing factor…
Relational Boosted Bandits
Ashutosh Kakadiya, Sriraam Natarajan, Balaraman Ravindran
Contextual bandits algorithms have become essential in real-world user interaction problems in recent years. However, these algorithms rely on context as attribute value representa…
Hypergraph Partitioning using Tensor Eigenvalue Decomposition
Deepak Maurya, Balaraman Ravindran
Hypergraphs have gained increasing attention in the machine learning community lately due to their superiority over graphs in capturing super-dyadic interactions among entities. In…
Goal directed molecule generation using Monte Carlo Tree Search
Anand A. Rajasekar, Karthik Raman, Balaraman Ravindran
One challenging and essential task in biochemistry is the generation of novel molecules with desired properties. Novel molecule generation remains a challenge since the molecule sp…
ADAIL: Adaptive Adversarial Imitation Learning
Yiren Lu, Jonathan Tompson
We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitati…
Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains
Nazneen N Sultana, Hardik Meisheri, Vinita Baniwal +3
This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. The problem description and solution are both adapted fr…
EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks
Sanchari Sen, Balaraman Ravindran, Anand Raghunathan
Ensuring robustness of Deep Neural Networks (DNNs) is crucial to their adoption in safety-critical applications such as self-driving cars, drones, and healthcare. Notably, DNNs are…
SEERL: Sample Efficient Ensemble Reinforcement Learning
Rohan Saphal, Balaraman Ravindran, Dheevatsa Mudigere +2
Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to their ability to tackle a wide range of instanc…
Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Arjun Manoharan, Rahul Ramesh, Balaraman Ravindran
Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent. However, such techniques often yield a…
Network Representation Learning: Consolidation and Renewed Bearing
Saket Gurukar, Priyesh Vijayan, Aakash Srinivasan +9
Graphs are a natural abstraction for many problems where nodes represent entities and edges represent a relationship across entities. An important area of research that has emerged…
ExTra: Transfer-guided Exploration
Anirban Santara, Rishabh Madan, Balaraman Ravindran +1
In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encou…
Learning Interpretable Models Using Uncertainty Oracles
Abhishek Ghose, Balaraman Ravindran
A desirable property of interpretable models is small size, so that they are easily understandable by humans. This leads to the following challenges: (a) small sizes typically impl…
MaMiC: Macro and Micro Curriculum for Robotic Reinforcement Learning
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. This makes the problem less complex a…
Successor Options: An Option Discovery Framework for Reinforcement Learning
Rahul Ramesh, Manan Tomar, Balaraman Ravindran
The options framework in reinforcement learning models the notion of a skill or a temporally extended sequence of actions. The discovery of a reusable set of skills has typically e…
Interpretability with Accurate Small Models
Abhishek Ghose, Balaraman Ravindran
Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of dept…
An Active Learning Framework for Efficient Robust Policy Search
Sai Kiran Narayanaswami, Nandan Sudarsanam, Balaraman Ravindran
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for tra…
Hypergraph Clustering: A Modularity Maximization Approach
Tarun Kumar, Sankaran Vaidyanathan, Harini Ananthapadmanabhan +2
Clustering on hypergraphs has been garnering increased attention with potential applications in network analysis, VLSI design and computer vision, among others. In this work, we ge…
Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning
Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra +1
Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filt…