Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Siddhartha Banerjee

Siddhartha Banerjee

Adaptive Discretization in Online Reinforcement Learning


Oct 29, 2021
Sean R. Sinclair, Siddhartha Banerjee, Christina Lee Yu

Figure 1 for Adaptive Discretization in Online Reinforcement Learning
Figure 2 for Adaptive Discretization in Online Reinforcement Learning
Figure 3 for Adaptive Discretization in Online Reinforcement Learning
Figure 4 for Adaptive Discretization in Online Reinforcement Learning
* 70 pages, 5 figures. arXiv admin note: text overlap with arXiv:2007.00717 
  Access Paper or Ask Questions

Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery


Jan 05, 2021
Devleena Das, Siddhartha Banerjee, Sonia Chernova

Figure 1 for Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery
Figure 2 for Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery
Figure 3 for Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery
Figure 4 for Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery

  Access Paper or Ask Questions

Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery


Nov 19, 2020
Devleena Das, Siddhartha Banerjee, Sonia Chernova

Figure 1 for Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery
Figure 2 for Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery
Figure 3 for Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery
Figure 4 for Explainable AI for System Failures: Generating Explanations that Improve Human Assistance in Fault Recovery

  Access Paper or Ask Questions

Adaptive Discretization for Model-Based Reinforcement Learning


Jul 01, 2020
Sean R. Sinclair, Tianyu Wang, Gauri Jain, Siddhartha Banerjee, Christina Lee Yu

Figure 1 for Adaptive Discretization for Model-Based Reinforcement Learning
Figure 2 for Adaptive Discretization for Model-Based Reinforcement Learning
Figure 3 for Adaptive Discretization for Model-Based Reinforcement Learning
Figure 4 for Adaptive Discretization for Model-Based Reinforcement Learning
* 50 pages, 6 figures 
  Access Paper or Ask Questions

Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks


Jan 28, 2020
Siddhartha Banerjee, Angel Daruna, David Kent, Weiyu Liu, Jonathan Balloch, Abhinav Jain, Akshay Krishnan, Muhammad Asif Rana, Harish Ravichandar, Binit Shah, Nithin Shrivatsav, Sonia Chernova

Figure 1 for Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks
Figure 2 for Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks
Figure 3 for Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks
Figure 4 for Taking Recoveries to Task: Recovery-Driven Development for Recipe-based Robot Tasks
* Published and presented at International Symposium on Robotics Research (ISRR), 2019 in Hanoi, Vietnam 
  Access Paper or Ask Questions

Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces


Oct 31, 2019
Sean R. Sinclair, Siddhartha Banerjee, Christina Lee Yu

Figure 1 for Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces
Figure 2 for Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces
Figure 3 for Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces
Figure 4 for Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces
* 46 pages, 15 figures 
  Access Paper or Ask Questions

Online Allocation and Pricing: Constant Regret via Bellman Inequalities


Jun 14, 2019
Alberto Vera, Siddhartha Banerjee, Itai Gurvich

Figure 1 for Online Allocation and Pricing: Constant Regret via Bellman Inequalities
Figure 2 for Online Allocation and Pricing: Constant Regret via Bellman Inequalities
Figure 3 for Online Allocation and Pricing: Constant Regret via Bellman Inequalities
Figure 4 for Online Allocation and Pricing: Constant Regret via Bellman Inequalities

  Access Paper or Ask Questions

The Bayesian Prophet: A Low-Regret Framework for Online Decision Making


Jan 15, 2019
Alberto Vera, Siddhartha Banerjee

Figure 1 for The Bayesian Prophet: A Low-Regret Framework for Online Decision Making
Figure 2 for The Bayesian Prophet: A Low-Regret Framework for Online Decision Making
Figure 3 for The Bayesian Prophet: A Low-Regret Framework for Online Decision Making
* Extended abstract to appear in SIGMETRICS 2019 
  Access Paper or Ask Questions

Effects of Interruptibility-Aware Robot Behavior


Apr 17, 2018
Siddhartha Banerjee, Andrew Silva, Karen Feigh, Sonia Chernova

Figure 1 for Effects of Interruptibility-Aware Robot Behavior
Figure 2 for Effects of Interruptibility-Aware Robot Behavior
Figure 3 for Effects of Interruptibility-Aware Robot Behavior
Figure 4 for Effects of Interruptibility-Aware Robot Behavior

  Access Paper or Ask Questions

Summarizing Situational and Topical Information During Crises


Oct 05, 2016
Koustav Rudra, Siddhartha Banerjee, Niloy Ganguly, Pawan Goyal, Muhammad Imran, Prasenjit Mitra

Figure 1 for Summarizing Situational and Topical Information During Crises
Figure 2 for Summarizing Situational and Topical Information During Crises
Figure 3 for Summarizing Situational and Topical Information During Crises
Figure 4 for Summarizing Situational and Topical Information During Crises
* 7 pages, 9 figures, Accepted in The 4th International Workshop on Social Web for Disaster Management (SWDM'16) will be co-located with CIKM 2016 
  Access Paper or Ask Questions

Abstractive Meeting Summarization UsingDependency Graph Fusion


Sep 22, 2016
Siddhartha Banerjee, Prasenjit Mitra, Kazunari Sugiyama

Figure 1 for Abstractive Meeting Summarization UsingDependency Graph Fusion
Figure 2 for Abstractive Meeting Summarization UsingDependency Graph Fusion
Figure 3 for Abstractive Meeting Summarization UsingDependency Graph Fusion
Figure 4 for Abstractive Meeting Summarization UsingDependency Graph Fusion
* WWW '15 Companion Proceedings of the 24th International Conference on World Wide Web, Pages 5-6. arXiv admin note: substantial text overlap with arXiv:1609.07033 
  Access Paper or Ask Questions

Multi-document abstractive summarization using ILP based multi-sentence compression


Sep 22, 2016
Siddhartha Banerjee, Prasenjit Mitra, Kazunari Sugiyama

Figure 1 for Multi-document abstractive summarization using ILP based multi-sentence compression
Figure 2 for Multi-document abstractive summarization using ILP based multi-sentence compression
Figure 3 for Multi-document abstractive summarization using ILP based multi-sentence compression
Figure 4 for Multi-document abstractive summarization using ILP based multi-sentence compression
* IJCAI'15 Proceedings of the 24th International Conference on Artificial Intelligence, Pages 1208-1214, AAAI Press 
  Access Paper or Ask Questions

Generating Abstractive Summaries from Meeting Transcripts


Sep 22, 2016
Siddhartha Banerjee, Prasenjit Mitra, Kazunari Sugiyama

Figure 1 for Generating Abstractive Summaries from Meeting Transcripts
Figure 2 for Generating Abstractive Summaries from Meeting Transcripts
Figure 3 for Generating Abstractive Summaries from Meeting Transcripts
Figure 4 for Generating Abstractive Summaries from Meeting Transcripts
* 10 pages, Proceedings of the 2015 ACM Symposium on Document Engineering, DocEng' 2015 
  Access Paper or Ask Questions

Unbounded Human Learning: Optimal Scheduling for Spaced Repetition


Jun 08, 2016
Siddharth Reddy, Igor Labutov, Siddhartha Banerjee, Thorsten Joachims

Figure 1 for Unbounded Human Learning: Optimal Scheduling for Spaced Repetition
Figure 2 for Unbounded Human Learning: Optimal Scheduling for Spaced Repetition
Figure 3 for Unbounded Human Learning: Optimal Scheduling for Spaced Repetition
Figure 4 for Unbounded Human Learning: Optimal Scheduling for Spaced Repetition
* Accepted to the ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2016 
  Access Paper or Ask Questions

Online Collaborative-Filtering on Graphs


Nov 07, 2014
Siddhartha Banerjee, Sujay Sanghavi, Sanjay Shakkottai

Figure 1 for Online Collaborative-Filtering on Graphs
Figure 2 for Online Collaborative-Filtering on Graphs

  Access Paper or Ask Questions

The Price of Privacy in Untrusted Recommendation Engines


Oct 27, 2014
Siddhartha Banerjee, Nidhi Hegde, Laurent Massoulié

* Preliminary version presented at the 50th Allerton Conference, 2012 
  Access Paper or Ask Questions

Greedy Learning of Markov Network Structure


Feb 08, 2012
Praneeth Netrapalli, Siddhartha Banerjee, Sujay Sanghavi, Sanjay Shakkottai

Figure 1 for Greedy Learning of Markov Network Structure
Figure 2 for Greedy Learning of Markov Network Structure
* Preliminary version appeared in 48th Annual Allerton Conference on Communication, Control, and Computing, 2010. Full version submitted to JMLR 
  Access Paper or Ask Questions