Michael Zavlanos

Yoh Family Professor at @DukeEngineering

[Boyuan Chen @Boyuan__Chen]

We are looking for two robotics/autonomy faculties here at Duke University! Please help spread the word and apply!

We also have a position on computational and robotic system for surgery!

Please see job positings: 1) https://t.co/whU9jtNd1x and 2) https://t.co/LiGIO3Nz6J

[Boyuan Chen @Boyuan__Chen]

Excited to share our latest work on "Policy Stitching” published on CoRL 2023 this week! We focus on how to enable cross-body cross-task transfer towards general-purpose robots. 🚀 A thread (1/n).

[DukeAIHealth @DukeAIHealth]

Duke AI Health Director @PencinaPhd and Director of Governance and Evaluation of Health AI Systems, Nicoleta Economou, PhD, had the pleasure of meeting @RepGregMurphy today to discuss the work of @DukeAIHealth in healthcare #AI development and governance. https://t.co/s1W6WxJpui

[Hans Riess @hansmriess]

I'm excited to share our new paper w/ @mungowitz and @m_zavlanos introducing a decentralized mechanism for pricing and exchanging alternatives constrained by transaction costs: a thread 🧵 1/n

[DukeAIHealth @DukeAIHealth]

ICYMI: @DukeAIHealth's Nicoleta J. Economou, PhD, the founding director of the Algorithm-Based Clinical Decision Support (ABCDS) Oversight, was recently interviewed by @Duke_OSI's Emilia Chiscop-Head, PhD. Read the interview here: https://t.co/MxaxVsZxBc

[Boyuan Chen @Boyuan__Chen]

Our new lab at Duke University is looking for PhD students! We conduct research in robotics (both mechanical and computational), vision, machine learning, and reinforcement learning.

If you are excited about becoming a "full-stack roboticist". Please consider to join us! (1/n)

[Michael Zavlanos @m_zavlanos]

Exciting new postdoc opportunity @DukeU on ethical AI, at the intersection of engineering, law, and policy. For more information and to apply visit: https://t.co/bSgAMueHeV

[arXiv Daily @Arxiv_Daily]

Risk-Averse Multi-Armed Bandits with Unobserved Confounders: A Case Study in Emotion Regulation in Mobile Health
https://t.co/2F2rOjjVLL
by Yi Shen et al. including @drjessilyn
#TransferLearning #ComputerScience

[Michael Zavlanos @m_zavlanos]

Thrilled to share the news of my promotion to Full Professor @DukeU! I am grateful to all the amazing students (present and past), collaborators, colleagues, mentors, family and friends who have inspired me and supported me along the way. Thank you!

[Michael Zavlanos @m_zavlanos]

New preprint on risk-averse learning in online convex games: https://t.co/LQdoaEGoJC We address important challenges related to the estimation of the risk values and gradients using finite feedback.

[Michael Zavlanos @m_zavlanos]

Two postdoc positions @Duke on optimization and machine learning. Projects span robotics, cyber-physical systems, and healthcare/medicine (with Biostatistics & Bioinformatics). To learn about our research, visit https://t.co/aoyRpCLzN7. To apply, please e-mail me with a CV.

[Michael Zavlanos @m_zavlanos]

Excited to share the news that I have joined Amazon Robotics as an Amazon Scholar (on sabbatical leave from Duke)! Looking forward to new collaborations and research on robot autonomy! #Amazon #Robotics

[Michael Zavlanos @m_zavlanos]

Learning neural network controllers with closed-loop safety guarantees requires a lot of data. But what if these data are not available? Check out our new preprint on learning neural network controllers that can fail with grace: https://t.co/DGsWXq9NCi

[Michael Zavlanos @m_zavlanos]

How can one learn optimal policies in continuous space from demonstrator data with hidden contextual information? Check out our recent work on continuous transfer RL with unobserved context presented at #L4DC.

Paper: https://t.co/Yq0rv5F07m
Talk (min 53): https://t.co/9PrP5Q7iPy

[Michael Zavlanos @m_zavlanos]

Duke MEMS is hiring! If you are looking for a faculty position, please apply!

https://t.co/Tlua8K2wkk

[Michael Zavlanos @m_zavlanos]

New postdoctoral position on machine learning and AI at Duke University, with focus on algorithms as well as applications in robotics, cyber-physical systems, or healthcare/medicine. For more information and to apply, please visit the link: https://t.co/mbcmY56nkb

[Michael Zavlanos @m_zavlanos]

Residual feedback can also be used to efficiently estimate local policy gradients in distributed reinforcement learning, using local estimates of the global accumulated rewards that depend on partial state and action information only: https://t.co/91DgT8H5TC

[Michael Zavlanos @m_zavlanos]

Check out our latest preprint on a new one-point residual-feedback gradient estimator for zeroth-order online learning: https://t.co/hJKbVOZrUh It achieves similar learning rate as two-point estimators which, however, can not be used for online learning in practice.

[Michael Zavlanos @m_zavlanos]

@miroslav_pajic @DukeEngineering Congrats!!!