Showing 14 publications by Joe Watson
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Scherer C, Watson J, Gruner T, Palenicek D, Posner I et al. (2026)
BibTeX
@misc{coherentoffpoli-2026/6,
title={Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards},
author={Scherer C, Watson J, Gruner T, Palenicek D, Posner I et al.},
year = "2026"
}
XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies
Palenicek D, Vogt F, Watson J, Posner I, Kragic D et al. (2026)
BibTeX
@misc{xqcfdaccelerati-2026/5,
title={XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies},
author={Palenicek D, Vogt F, Watson J, Posner I, Kragic D et al.},
year = "2026"
}
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
Flynn H, Watson J, Posner I & Peters J (2026)
BibTeX
@misc{posteriorsampli-2026/3,
title={Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces},
author={Flynn H, Watson J, Posner I & Peters J},
year = "2026"
}
Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention
Baumgartner MW, Lei A, Watson J & Posner I (2026), Proceedings of Machine Learning Research, 323, 119-165
BibTeX
@inproceedings{disentanglingdy-2026/1,
title={Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention},
author={Baumgartner MW, Lei A, Watson J & Posner I},
pages={119-165},
year = "2026"
}
Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
Palenicek D, Vogt F, Watson J & Peters J (2025), Advances in Neural Information Processing Systems, 38, 68874-68896
BibTeX
@inproceedings{scalingoffpolic-2025/1,
title={Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization},
author={Palenicek D, Vogt F, Watson J & Peters J},
pages={68874-68896},
year = "2025"
}
Machine Learning with Physics Knowledge for Prediction: A Survey
Watson J, Song C, Weeger O, Gruner T, Le AT et al. (2024)
BibTeX
@misc{machinelearning-2024/8,
title={Machine Learning with Physics Knowledge for Prediction: A Survey},
author={Watson J, Song C, Weeger O, Gruner T, Le AT et al.},
year = "2024"
}
Coherent Soft Imitation Learning
Watson J, Huang SH & Heess N (2023)
BibTeX
@misc{coherentsoftimi-2023/5,
title={Coherent Soft Imitation Learning},
author={Watson J, Huang SH & Heess N},
year = "2023"
}
Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes
Watson J & Peters J (2022)
BibTeX
@misc{inferringsmooth-2022/10,
title={Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes},
author={Watson J & Peters J},
year = "2022"
}
Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference
Watson J, Abdulsamad H, Findeisen R & Peters J (2021)
BibTeX
@misc{efficientstocha-2021/5,
title={Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference},
author={Watson J, Abdulsamad H, Findeisen R & Peters J},
year = "2021"
}
Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk
Watson J & Peters J (2021)
BibTeX
@misc{advancingtrajec-2021/3,
title={Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk},
author={Watson J & Peters J},
year = "2021"
}
Differentiable physics models for real-world offline model-based reinforcement learning
Lutter M, Silberbauer J, Watson J & Peters J (2021), IEEE International Conference on Robotics and Automation (ICRA)
BibTeX
@inproceedings{differentiablep-2021/,
title={Differentiable physics models for real-world offline model-based reinforcement learning},
author={Lutter M, Silberbauer J, Watson J & Peters J},
year = "2021"
}
Active Inference or Control as Inference? A Unifying View
Watson J, Imohiosen A & Peters J (2020)
BibTeX
@misc{activeinference-2020/10,
title={Active Inference or Control as Inference? A Unifying View},
author={Watson J, Imohiosen A & Peters J},
year = "2020"
}
Stochastic Optimal Control as Approximate Input Inference
Watson J, Abdulsamad H & Peters J (2019)
BibTeX
@misc{stochasticoptim-2019/10,
title={Stochastic Optimal Control as Approximate Input Inference},
author={Watson J, Abdulsamad H & Peters J},
year = "2019"
}
Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation
Funk N, Schaff C, Madan R, Yoneda T, De Jesus JU et al. (0), IEEE Robotics and Automation Letters, 7(1), 478-485
BibTeX
@article{benchmarkingstr-/,
title={Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation},
author={Funk N, Schaff C, Madan R, Yoneda T, De Jesus JU et al.},
journal={IEEE Robotics and Automation Letters},
volume={7},
pages={478-485},
publisher={Institute of Electrical and Electronics Engineers (IEEE)}
}