2025

A Generalist Hanabi Agent

Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond, Miao Liu, Janarthanan Rajendran, Sarath Chandar

International Conference on Learning Representations (ICLR) 2025

[Paper] [arXiv]


Mitigating Unsafe Feedback with Learning Constraints

Domenic Rosati, Giles Edkins, Harsh Raj, David Atanasov, Subhabrata Majumdar, Janarthanan Rajendran, Frank Rudzicz, Hassan Sajjad

Workshop on Artificial Intelligence for Cyber Security (AICS) at AAAI 2025 

[arXiv]

2024

Balancing Context Length and Mixing Times for Reinforcement Learning at Scale

Matthew D Riemer, Khimya Khetarpal, Janarthanan Rajendran, Sarath Chandar

Neural Information Processing Systems (NeurIPS) 2024

[Paper]


Toward Debugging Deep Reinforcement Learning Programs with RLExplorer

Rached Bouchoucha, Ahmed Haj Yahmed, Darshan Patil, Janarthanan Rajendran, Amin Nikanjam, Sarath Chandar, Foutse Khomh

International Conference on Software Maintenance and Evolution (ICSME) 2024

[arXiv]


Dynamic Incentives in Response to Dynamic Pricing

Jesse Thibodeau, Hadi Nekoei, Afaf Taïk, Janarthanan Rajendran, Golnoosh Farnadi

Econometric Society Interdisciplinary Frontiers (ESIF) conference on Economics and AI+ML 2024


Mastering Memory Tasks with World Models

Mohammad Reza Samsami*, Artem Zholus*, Janarthanan Rajendran, Sarath Chandar

International Conference on Learning Representations (ICLR) 2024

Initial version was presented at the Workshop on Agent Learning in Open-Endedness (ALOE) at NeurIPS 2023

Ranked among the top 1.2 % of the 7304 submissions received at ICLR 2024

[Paper] [arXiv]


Intelligent Switching for Reset-Free Reinforcement Learning

Darshan Patil, Janarthanan Rajendran, Glen Berseth, Sarath Chandar

International Conference on Learning Representations (ICLR) 2024

[Paper] [arXiv]


2023

Learning Conditional Policies for Crystal Design Using Offline Reinforcement Learning

Prashant Govindarajan, Santiago Miret, Jarrid Rector-Brooks, Mariano Phielipp, Janarthanan Rajendran, Sarath Chandar

AI for Accelerated Materials Design (AI4Mat), Digital Discovery Journal 2023

[Paper]


Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning

Xutong Zhao, Yangchen Pan, Chenjun Xiao, Sarath Chandar, Janarthanan Rajendran

Conference on Uncertainty in Artificial Intelligence (UAI) 2023

[Paper] [arXiv]


Replay Buffer with Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning

Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar

Conference on Lifelong Learning Agents (CoLLAs) 2023

Initial version was presented at the Workshop on Deep Reinforcement Learning at NeurIPS 2022

Part of Ali's thesis that won the Canadian Artificial Intelligence Association (CAIAC) 2024 Best Master’s Thesis Award

[Paper] [arXiv]


Towards Few-shot Coordination: Revisiting Ad-Hoc Teamplay Challenge in the Game of Hanabi

Hadi Nekoei, Xutong Zhao, Janarthanan Rajendran, Miao Liu, Sarath Chandar

Conference on Lifelong Learning Agents (CoLLAs) 2023

[Paper] [arXiv


Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning

Hadi Nekoei, Akilesh Badrinaaraayanan, Amit Sinha, Mohammad Amini, Janarthanan Rajendran, Aditya Mahajan, Sarath Chandar

Conference on Lifelong Learning Agents (CoLLAs) 2023

Initial version was presented at the Workshop on Gamification and Multi-Agent Solutions at ICLR 2022

[Paper] [arXiv]


Behavior Cloning for Crystal Design

Prashant Govindarajan, Santiago Miret, Jarrid Rector-Brooks, Mariano Phielipp, Janarthanan Rajendran, Sarath Chandar

Workshop on Machine Learning for Materials at ICLR 2023


2022

PatchBlender: A Motion Prior for Video Transformers

Gabriele Prato, Yale Song, Janarthanan Rajendran, Devon Hjelm, Neel Joshi, Sarath Chandar

Workshop on Vision Transformers: Theory and Applications at NeurIPS 2022

[arXiv]


An Introduction to Lifelong Supervised Learning

Shagun Sodhani, Mojtaba Faramarzi, Sanket Vaibhav Mehta, Pranshu Malviya, Mohamed Abdelsalam, Janarthanan Rajendran, Sarath Chandar

arXiv 2022

[arXiv]


Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Yi Wan*, Ali Rahimi-Kalahroudi*, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen

International Conference on Machine Learning (ICML) 2022

Initial version was presented at the Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2022 and at the Workshop on Agent Learning in Open-Endedness (ALOE) at ICLR 2022

Part of Ali's thesis that won the Canadian Artificial Intelligence Association (CAIAC) 2024 Best Master’s Thesis Award

[Paper] [arXiv]



2021

Learning to Learn End-to-End Goal-Oriented Dialog from Related Tasks

Janarthanan Rajendran, Jonathan K. Kummerfeld, Satinder Singh

Workshop on NLP for Conversational AI at EMNLP 2021

[Paper] [arXiv]


Reinforcement Learning of Implicit and Explicit Control Flow in Instructions

Ethan A. Brooks, Janarthanan Rajendran, Richard L. Lewis, Satinder Singh

International Conference on Machine Learning (ICML) 2021

[Paper] [arXiv]


Understanding the Impact of COVID-19 on Online Mental Health Forums

Laura Biester, Katie Matton, Janarthanan Rajendran, Emily Mower Provost, Rada Mihalcea

ACM Transactions on Management Information Systems (TMIS) 2021

[Paper]


2020

Meta-Learning Requires Meta-Augmentation

Janarthanan Rajendran*, Alex Irpan*, Eric Jang* 

Neural Information Processing Systems (NeurIPS) 2020

[Paper] [arXiv]


Quantifying the Effects of COVID-19 on Mental Health Support Forums

Laura Biester*, Katie Matton*, Janarthanan Rajendran, Emily Mower Provost, Rada Mihalcea 

Workshop on NLP for COVID-19 at EMNLP 2020

[Paper] [arXiv]


How Should an Agent Practice?

Janarthanan Rajendran, Richard Lewis, Vivek Veeriah, Honglak Lee, Satinder Singh 

Association for the Advancement of Artificial Intelligence (AAAI) 2020

[Paper] [arXiv]


2019

The Discovery of Useful Questions as Auxiliary Tasks

Vivek Veeriah, Matteo Hessel, Zhongwen Xu, Janarthanan Rajendran, Richard Lewis, Junhyuk Oh, Hado van Hasselt, David Silver, Satinder Singh

Neural Information Processing Systems (NeurIPS) 2019

[Paper] [arXiv]


Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use

Janarthanan Rajendran, Jatin Ganhotra, Lazaros C. Polymenakos

Transactions of the Association for Computational Linguistics (TACL) 2019

[Paper] [arXiv]


NE-Table: A Neural Key-Value Table for Named Entities

Janarthanan Rajendran*, Jatin Ganhotra*, Xiaoxiao Guo, Mo Yu, Satinder Singh, Lazaros C. Polymenakos

Recent Advances in Natural Language Processing (RANLP) 2019

[Paper] [arXiv]


2018

Learning End-to-End Goal-Oriented Dialog With Multiple Answers

Janarthanan Rajendran*, Jatin Ganhotra*, Satinder Singh, Lazaros C. Polymenakos

Empirical Methods in Natural Language Processing (EMNLP) 2018

[Paper] [arXiv]


2017

Attend, Adapt, and Transfer: Attentive Deep Architecture for Adaptive Transfer From Multiple Sources in the Same Domain

Janarthanan Rajendran*, Aravind S. Lakshminarayanan*, Mitesh M. Khapra, Prasanna Parthasarathi, Balaraman Ravindran

International Conference on Learning Representations (ICLR) 2017

Initial version was presented at the Workshop on Deep Reinforcement Learning at NeurIPS 2015

[Paper] [arXiv]


2016

Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning

Janarthanan Rajendran, Mitesh M. Khapra, Sarath Chandar, Balaraman Ravindran

North American Chapter of the Association of Computational Linguistics (NAACL) 2016

Initial version was presented in the Workshop on Multimodal Machine Learning, NeurIPS 2015

Mentioned in the article 'The Top AI Breakthroughs of 2015' by the Future of Life Institute

[Paper] [arXiv]


A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation

Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran, Kyunghyun Cho

International Conference on Computational Linguistics (COLING ) 2016

[Paper] [arXiv]


2015

Stability and Bifurcation Analysis of a Pupillary Light Reflex Model

Janarthanan Rajendran, Sivashyam Sundar Arutprakasam, Amit M. Warrier

Control and Decision Conference (CCDC ) 2015

[Paper]


2014

How Popular Are Your Tweets?

Avijit Saha, Janarthanan Rajendran, Shubhranshu Shekhar, Balaraman Ravindran

Workshop on the Recommender Systems Challenge at RecSys 2014

[Paper]