Pulkit Agrawal

papers

704

total citations

papers (15)

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

NEURIPS 2023arXiv

citations

Self-Adapting Language Models

NEURIPS 2025arXiv

citations

Distributionally Adaptive Meta Reinforcement Learning

NEURIPS 2022arXiv

citations

Language Model Personalization via Reward Factorization

COLM 2025arXiv

citations

Self-Supervised Reinforcement Learning that Transfers using Random Features

NEURIPS 2023arXiv

citations

Random Latent Exploration for Deep Reinforcement Learning

ICML 2024arXiv

citations

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective

ICML 2025arXiv

citations

Human-Guided Complexity-Controlled Abstractions

NEURIPS 2023arXiv

citations

Position: Automatic Environment Shaping is the Next Frontier in RL

ICML 2024

citations

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

NEURIPS 2023

citations

Pulkit Agrawal

papers (15)

OpenEQA: Embodied Question Answering in the Era of Foundation Models

Diffusion Policy Policy Optimization

Compositional Foundation Models for Hierarchical Planning

Curiosity-driven Red-teaming for Large Language Models

Redeeming intrinsic rewards via constrained optimization

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Self-Adapting Language Models

Distributionally Adaptive Meta Reinforcement Learning

Language Model Personalization via Reward Factorization

Self-Supervised Reinforcement Learning that Transfers using Random Features

Random Latent Exploration for Deep Reinforcement Learning

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective

Human-Guided Complexity-Controlled Abstractions

Position: Automatic Environment Shaping is the Next Frontier in RL

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

papers (15)

OpenEQA: Embodied Question Answering in the Era of Foundation Models

Diffusion Policy Policy Optimization

Compositional Foundation Models for Hierarchical Planning

Curiosity-driven Red-teaming for Large Language Models

Redeeming intrinsic rewards via constrained optimization

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Self-Adapting Language Models

Distributionally Adaptive Meta Reinforcement Learning

Language Model Personalization via Reward Factorization

Self-Supervised Reinforcement Learning that Transfers using Random Features

Random Latent Exploration for Deep Reinforcement Learning

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective

Human-Guided Complexity-Controlled Abstractions

Position: Automatic Environment Shaping is the Next Frontier in RL

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