Abhishek Gupta

papers

2,227

total citations

papers (16)

Gradient Surgery for Multi-Task Learning

NEURIPS 2020arXiv

1,580

citations

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

NEURIPS 2021arXiv

247

citations

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

NEURIPS 2020arXiv

118

citations

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

NEURIPS 2022arXiv

citations

RoboHive: A Unified Framework for Robot Learning

NEURIPS 2023arXiv

citations

Autonomous Reinforcement Learning via Subgoal Curricula

NEURIPS 2021arXiv

citations

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

NEURIPS 2023arXiv

citations

STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning

ICLR 2025arXiv

citations

Distributionally Adaptive Meta Reinforcement Learning

NEURIPS 2022arXiv

citations

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

NEURIPS 2023arXiv

citations

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

NEURIPS 2021arXiv

citations

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

NEURIPS 2023

citations

Abhishek Gupta

papers (16)

Gradient Surgery for Multi-Task Learning

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

RoboHive: A Unified Framework for Robot Learning

Autonomous Reinforcement Learning via Subgoal Curricula

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning

Distributionally Adaptive Meta Reinforcement Learning

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

DRAWER: Digital Reconstruction and Articulation With Environment Realism

Self-Supervised Reinforcement Learning that Transfers using Random Features

Teachable Reinforcement Learning via Advice Distillation

Graph Learning Assisted Multi-Objective Integer Programming

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

papers (16)

Gradient Surgery for Multi-Task Learning

Adaptive Risk Minimization: Learning to Adapt to Domain Shift

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

RoboHive: A Unified Framework for Robot Learning

Autonomous Reinforcement Learning via Subgoal Curricula

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning

Distributionally Adaptive Meta Reinforcement Learning

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

DRAWER: Digital Reconstruction and Articulation With Environment Realism

Self-Supervised Reinforcement Learning that Transfers using Random Features

Teachable Reinforcement Learning via Advice Distillation

Graph Learning Assisted Multi-Objective Integer Programming

Which Mutual-Information Representation Learning Objectives are Sufficient for Control?

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback