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

Add to Chrome

Add to Firefox

Picture for Khimya Khetarpal

Khimya Khetarpal

POMRL: No-Regret Learning-to-Plan with Increasing Horizons

Dec 30, 2022
Khimya Khetarpal, Claire Vernade, Brendan O'Donoghue, Satinder Singh, Tom Zahavy

Figure 1 for POMRL: No-Regret Learning-to-Plan with Increasing Horizons

Figure 2 for POMRL: No-Regret Learning-to-Plan with Increasing Horizons

Figure 3 for POMRL: No-Regret Learning-to-Plan with Increasing Horizons

Figure 4 for POMRL: No-Regret Learning-to-Plan with Increasing Horizons

* 24 pages, 6 figures

Access Paper or Ask Questions

The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning

Jan 24, 2022
Andrei Nica, Khimya Khetarpal, Doina Precup

* 20 pages, 15 figures

Access Paper or Ask Questions

Temporally Abstract Partial Models

Aug 06, 2021
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, Doina Precup

Figure 1 for Temporally Abstract Partial Models

Figure 2 for Temporally Abstract Partial Models

Figure 3 for Temporally Abstract Partial Models

Figure 4 for Temporally Abstract Partial Models

* 34 pages, 5 figures

Access Paper or Ask Questions

Variance Penalized On-Policy and Off-Policy Actor-Critic

Feb 03, 2021
Arushi Jain, Gandharv Patil, Ayush Jain, Khimya Khetarpal, Doina Precup

Figure 1 for Variance Penalized On-Policy and Off-Policy Actor-Critic

Figure 2 for Variance Penalized On-Policy and Off-Policy Actor-Critic

Figure 3 for Variance Penalized On-Policy and Off-Policy Actor-Critic

Figure 4 for Variance Penalized On-Policy and Off-Policy Actor-Critic

* Accepted to the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021

Access Paper or Ask Questions

Towards Continual Reinforcement Learning: A Review and Perspectives

Dec 25, 2020
Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup

Figure 1 for Towards Continual Reinforcement Learning: A Review and Perspectives

Figure 2 for Towards Continual Reinforcement Learning: A Review and Perspectives

Figure 3 for Towards Continual Reinforcement Learning: A Review and Perspectives

Figure 4 for Towards Continual Reinforcement Learning: A Review and Perspectives

* Preprint, 52 pages, 8 figures

Access Paper or Ask Questions

Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Jul 28, 2020
Amy Zhang, Shagun Sodhani, Khimya Khetarpal, Joelle Pineau

Figure 1 for Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Figure 2 for Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Figure 3 for Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

Figure 4 for Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP

* Accepted at the ICML 2020 Workshop on Theoretical Foundations of Reinforcement Learning. 21 pages, 12 figures

Access Paper or Ask Questions

What can I do here? A Theory of Affordances in Reinforcement Learning

Jun 26, 2020
Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup

Figure 1 for What can I do here? A Theory of Affordances in Reinforcement Learning

Figure 2 for What can I do here? A Theory of Affordances in Reinforcement Learning

Figure 3 for What can I do here? A Theory of Affordances in Reinforcement Learning

Figure 4 for What can I do here? A Theory of Affordances in Reinforcement Learning

* Thirty-seventh International Conference on Machine Learning (ICML 2020)

Access Paper or Ask Questions

Options of Interest: Temporal Abstraction with Interest Functions

Jan 01, 2020
Khimya Khetarpal, Martin Klissarov, Maxime Chevalier-Boisvert, Pierre-Luc Bacon, Doina Precup

Figure 1 for Options of Interest: Temporal Abstraction with Interest Functions

Figure 2 for Options of Interest: Temporal Abstraction with Interest Functions

Figure 3 for Options of Interest: Temporal Abstraction with Interest Functions

Figure 4 for Options of Interest: Temporal Abstraction with Interest Functions

* To appear in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20)

Access Paper or Ask Questions