no code implementations • 12 Jul 2023 • Jihao Andreas Lin, Joe Watson, Pascal Klink, Jan Peters
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior.
1 code implementation • NeurIPS 2023 • Joe Watson, Sandy H. Huang, Nicolas Heess
Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward.
1 code implementation • 7 Oct 2022 • Joe Watson, Jan Peters
Monte Carlo methods have become increasingly relevant for control of non-differentiable systems, approximate dynamics models and learning from data.
no code implementations • 29 Sep 2021 • Jihao Andreas Lin, Joe Watson, Pascal Klink, Jan Peters
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior predictive distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior.
1 code implementation • 17 May 2021 • Joe Watson, Hany Abdulsamad, Rolf Findeisen, Jan Peters
Optimal control under uncertainty is a prevailing challenge for many reasons.
1 code implementation • 10 Mar 2021 • Joe Watson, Jan Peters
Discrete-time stochastic optimal control remains a challenging problem for general, nonlinear systems under significant uncertainty, with practical solvers typically relying on the certainty equivalence assumption, replanning and/or extensive regularization.
no code implementations • pproximateinference AABI Symposium 2021 • Joe Watson, Jihao Andreas Lin, Pascal Klink, Jan Peters
Neural linear models (NLM) and Gaussian processes (GP) are both examples of Bayesian linear regression on rich feature spaces.
no code implementations • 3 Nov 2020 • Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters
A limitation of model-based reinforcement learning (MBRL) is the exploitation of errors in the learned models.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 19 Oct 2020 • Michael Lutter, Johannes Silberbauer, Joe Watson, Jan Peters
In this work, we examine a spectrum of hybrid model for the domain of multi-body robot dynamics.
no code implementations • 1 Oct 2020 • Joe Watson, Abraham Imohiosen, Jan Peters
Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation.
1 code implementation • Conference on Robot Learning (CoRL) 2019 2019 • Joe Watson, Hany Abdulsamad, Jan Peters
Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning.