Vivek Myers

I’m a PhD student at Berkeley Artificial Intelligence Research (BAIR) advised by Anca Dragan and Sergey Levine with support from an NDSEG fellowship. My research interests include reinforcement learning, human-robot interaction, and robotics. Before coming to Berkeley, I got my bachelor's degree in Computer Science and Mathematics at Stanford University, where I worked with Dorsa Sadigh.

me

Preprints

planning
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
Benjamin EysenbachVivek MyersRuslan SalakhutdinovSergey Levine

Publications

palo
Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation
Vivek MyersBill Chunyuan ZhengOier MeesSergey LevineKuan Fang
Conference on Robot Learning (CoRL), 2024
metrics
Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
Vivek MyersChongyi ZhengAnca DraganSergey LevineBenjamin Eysenbach
International Conference on Machine Learning (ICML), 2024
coproc
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
Michelle PanMariah SchrumVivek MyersErdem BıyıkAnca Dragan
International Conference on Machine Learning (ICML), 2024
social
Toward Grounded Commonsense Reasoning
Minae KwonHengyuan HuVivek MyersSiddharth KaramchetiAnca DraganDorsa Sadigh
IEEE International Conference on Robotics and Automation (ICRA), 2024
bridge
BridgeData V2: A Dataset for Robot Learning at Scale
Homer WalkeKevin BlackAbraham LeeMoo Jin KimMax DuChongyi ZhengTony ZhaoPhilippe Hansen-EstruchQuan VuongAndre HeVivek MyersKuan FangChelsea FinnSergey Levine
Conference on Robot Learning (CoRL), 2023
grif
Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control
Vivek MyersAndre HeKuan FangHomer WalkePhillipe Hansen-EstruchChing-An ChengMihai JalobeanuAndrey KolobovAnca DraganSergey Levine
Conference on Robot Learning (CoRL), 2023
query
Active Reward Learning from Online Preferences
Vivek MyersErdem BıyıkDorsa Sadigh
IEEE International Conference on Robotics and Automation (ICRA), 2023
rankings
Learning Multimodal Rewards from Rankings
Vivek MyersErdem BıyıkNima AnariDorsa Sadigh
Conference on Robot Learning (CoRL), 2021 (Oral Presentation)
surrogates
Effective Surrogate Models for Protein Design with Bayesian Optimization
Nate GruverSamuel StantonPolina KirichenkoMarc FinziPhillip MaffettoneVivek MyersEmily DelaneyPeyton GreensideAndrew Gordon Wilson
ICML 2021 Workshop on Computational Biology
hbbs
A Hierarchical Approach to Scaling Batch Active Search Over Structured Data
Vivek MyersPeyton Greenside
ICML 2020 Workshop on Real World Experiment Design and Active Learning