Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by A. Rupam
Computer Science > Machine Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2510.06277] General and Efficient Visual Goal-Conditioned Reinforcement Learning using Object-Agnostic Masks
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
AVG-DICE: Stationary Distribution Correction by Regression
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2410.14606] Streaming Deep Reinforcement Learning Finally Works
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2306.13812v2] Loss of Plasticity in Deep Continual Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2306.13812] Maintaining Plasticity in Deep Continual Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2306.13284] Correcting discount-factor mismatch in on-policy policy gradient methods
The policy gradient theorem gives a convenient form of the policy gradient in terms of three factors: an action value, a gradient of the action likelihood, and a state distribution involving discounting called the \emph{discounted stationary distribution}.
[2305.05760] Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization
[Submitted on 9 May 2023 ( v1 ), last revised 31 May 2023 (this version, v2)] Title:Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization Download a PDF of the paper titled Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization, by Homayoon Farrahi and A. Rupam Mahmood Download PDF Abstract: Continuous-time reinforcement learning tasks commonly use discrete steps of fixed cycle times for actions.
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
arXiv:2302.03281 (cs) [Submitted on 7 Feb 2023 (v1), last revised 27 Apr 2023 (this version, v2)] Download a PDF of the paper titled Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning, by Mohamed Elsayed and 1 other authors Download PDF Submission history From: Mohamed Elsayed [ view email] [v1] Tue, 7 Feb 2023 06:14:48 UTC (28,693 KB) [v2] Thu, 27 Apr 2023 17:54:58 UTC (9,175 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps...
[2302.01470] Learning to Optimize for Reinforcement Learning
[Submitted on 3 Feb 2023 ( v1 ), last revised 2 Jul 2023 (this version, v2)] Title:Learning to Optimize for Reinforcement Learning Download a PDF of the paper titled Learning to Optimize for Reinforcement Learning, by Qingfeng Lan and 3 other authors Download PDF Abstract: In recent years, by leveraging more data, computation, and diverse tasks, learned optimizers have achieved remarkable success in supervised learning, outperforming classical hand-designed optimizers.
[2212.04407] Variable Decision-Frequency Option Critic
[Submitted on 6 Dec 2022 ( v1 ), last revised 23 Jun 2023 (this version, v3)] Title:Variable Decision-Frequency Option Critic Download a PDF of the paper titled Variable Decision-Frequency Option Critic, by Amirmohammad Karimi and 4 other authors Download PDF Abstract: In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals.
[2210.02317] Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers
[Submitted on 5 Oct 2022 ( v1 ), last revised 26 Jun 2023 (this version, v2)] Title:Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers Download a PDF of the paper titled Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers, by Yan Wang and 2 other authors Download PDF Abstract: Real-time learning is crucial for robotic agents adapting to ever-changing, non-stationary environments.
[1809.07731] Benchmarking Reinforcement Learning Algorithms on Real-World Robots
Abstract: Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on these results due to open source implementations of learning algorithms and simulated benchmark tasks.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with A.
Contact A., search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack