Pulkit Agrawal

ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization ICLR 2025 Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation RSS 2025 Robot Learning with Super-Linear Scaling RSS 2025 Position: General Intelligence Requires Reward-based Pretraining ICML 2025 Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective ICML 2025 Diffusion Policy Policy Optimization ICLR 2025 Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning ICLR 2025 Position: Automatic Environment Shaping is the Next Frontier in RL ICML 2024 Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient NIPS 2024 Few-Shot Task Learning through Inverse Generative Modeling NIPS 2024 Going Beyond Heuristics by Imposing Policy Improvement as a Constraint NIPS 2024 Action Space Design in Reinforcement Learning for Robot Motor Skills CORL 2024 OpenEQA: Embodied Question Answering in the Era of Foundation Models CVPR 2024 Curiosity-driven Red-teaming for Large Language Models ICLR 2024 Random Latent Exploration for Deep Reinforcement Learning ICML 2024 Reconciling Reality through Simulation: A Real-To-Sim-to-Real Approach for Robust Manipulation RSS 2024 Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets NIPS 2023 Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks ICML 2023 Learning to Extrapolate: A Transductive Approach ICLR 2023 Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting ICLR 2023 Is Conditional Generative Modeling all you need for Decision Making? ICLR 2023 Compositional Foundation Models for Hierarchical Planning NIPS 2023 Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback NIPS 2023 Self-Supervised Reinforcement Learning that Transfers using Random Features NIPS 2023 Human-Guided Complexity-Controlled Abstractions NIPS 2023 Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback CORL 2023 Statistical Learning under Heterogeneous Distribution Shift ICML 2023 TGRL: An Algorithm for Teacher Guided Reinforcement Learning ICML 2023 Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation ICML 2023 Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation ICML 2023 Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement CORL 2023 Learning to See Physical Properties with Active Sensing Motor Policies CORL 2023 Topological Experience Replay ICLR 2022 Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior CORL 2022 SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields CORL 2022 Efficient Tactile Simulation with Differentiability for Robotic Manipulation CORL 2022 Rapid Locomotion via Reinforcement Learning RSS 2022 Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations ICLR 2022 Overcoming The Spectral Bias of Neural Value Approximation ICLR 2022 Bi-linear Value Networks for Multi-goal Reinforcement Learning ICLR 2022 Offline RL Policies Should Be Trained to be Adaptive ICML 2022 Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning ICML 2022 Redeeming intrinsic rewards via constrained optimization NIPS 2022 Distributionally Adaptive Meta Reinforcement Learning NIPS 2022 Learning Task Informed Abstractions ICML 2021 3D Neural Scene Representations for Visuomotor Control CORL 2021 The Task Specification Problem CORL 2021 OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning ICLR 2021 A System for General In-Hand Object Re-Orientation CORL 2021 An End-to-End Differentiable Framework for Contact-Aware Robot Design RSS 2021 Learning to Jump from Pixels CORL 2021 AdaScale SGD: A User-Friendly Algorithm for Distributed Training ICML 2020 A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects CORL 2020 Superposition of many models into one NIPS 2019 Investigating Human Priors for Playing Video Games ICML 2018 Zero-Shot Visual Imitation ICLR 2018 What Will Happen Next? Forecasting Player Moves in Sports Videos ICCV 2017 Curiosity-driven Exploration by Self-supervised Prediction ICML 2017 Learning to Poke by Poking: Experiential Learning of Intuitive Physics NIPS 2016 Human Pose Estimation With Iterative Error Feedback CVPR 2016 Learning to See by Moving ICCV 2015