JW
Joe Watson
cs.LGcs.ROcs.SYeess.SYstat.MLcs.AIcs.NAmath.NAphysics.comp-phstat.AP
On Valency
published · living versionsW_p8cd8pn6·v1 · currentpublished
A Battery for AI Propensity Measurement: Rubrics, Synthetic Item Banks, and Annotations
with Peter Romero, Haotian Li, Hugo Save, Luning Sun +6
1 version
Preprints & journals
20 papers in the corpus · 2019–2026PneuTac: Tactile Manipulation with Soft Pneumatic Robots via Unified MPM-Gaussian Splatting Simulation2609.38418v1 · Shaohong Zhong, Marco Pontin, Joe Watson et al.2026 · 0 citationsarXiv
Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention2603.14483v2 · Markus W. Baumgartner, Anson Lei, Joe Watson et al.2026 · 0 citationsProceedings of Machine Learning Research 323, 2026
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces2603.08287v3 · Hamish Flynn, Joe Watson, Ingmar Posner et al.2026 · 0 citationsarXiv
Building Gradient by Gradient: Decentralised Energy Functions for Bimanual Robot Assembly2510.04696v2 · Alexander L. Mitchell, Joe Watson, Ingmar Posner2025 · 0 citationsarXiv
XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning2509.25174v2 · Daniel Palenicek, Florian Vogt, Joe Watson et al.2025 · 0 citationsarXiv
Towards Safe Robot Foundation Models Using Inductive Biases2505.10219v1 · Maximilian Tolle, Theo Gruner, Daniel Palenicek et al.2025 · 0 citationsarXiv
Global Tensor Motion Planning2411.19393v3 · An T. Le, Kay Hansel, Joao Carvalho et al.2024 · 2 citationsarXiv
Machine Learning with Physics Knowledge for Prediction: A Survey2408.09840v2 · Joe Watson, Chen Song, Oliver Weeger et al.2024 · 4 citationsarXiv
Function-Space Regularization for Deep Bayesian Classification2307.06055v1 · Jihao Andreas Lin, Joe Watson, Pascal Klink et al.2023 · 0 citationsarXiv
Coherent Soft Imitation Learning2305.16498v3 · Joe Watson, Sandy H. Huang, Nicolas Heess2023 · 0 citationsarXiv
Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes2210.03512v1 · Joe Watson, Jan Peters2022 · 3 citationsarXiv
A Differentiable Newton-Euler Algorithm for Real-World Robotics2110.12422v1 · Michael Lutter, Johannes Silberbauer, Joe Watson et al.2021 · 2 citationsarXiv
Real Robot Challenge: A Robotics Competition in the Cloud2109.10957v2 · Stefan Bauer, Felix Widmaier, Manuel Wuthrich et al.2021 · 5 citationsarXiv
Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference2105.07693v2 · Joe Watson, Hany Abdulsamad, Rolf Findeisen et al.2021 · 3 citationsarXiv
Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation2105.02087v2 · Niklas Funk, Charles Schaff, Rishabh Madan et al.2021 · 24 citationsIEEE Robotics and Automation Letters 7 (2022) 478-485
Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk2103.06319v1 · Joe Watson, Jan Peters2021 · 6 citationsarXiv
Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning2011.01734v1 · Michael Lutter, Johannes Silberbauer, Joe Watson et al.2020 · 34 citationsarXiv
A Differentiable Newton Euler Algorithm for Multi-body Model Learning2010.09802v1 · Michael Lutter, Johannes Silberbauer, Joe Watson et al.2020 · 9 citationsarXiv
Active Inference or Control as Inference? A Unifying View2010.00262v1 · Joe Watson, Abraham Imohiosen, Jan Peters2020 · 13 citationsarXiv
Stochastic Optimal Control as Approximate Input Inference1910.03003v2 · Joe Watson, Hany Abdulsamad, Jan Peters2019 · 23 citationsarXiv
Career total: 28 works. 20 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.