Skid raw: Skill discovery from raw trajectories
D Tanneberg, K Ploeger, E Rueckert… - IEEE robotics and …, 2021 - ieeexplore.ieee.org
Integrating robots in complex everyday environments requires a multitude of problems to be
solved. One crucial feature among those is to equip robots with a mechanism for teaching …
solved. One crucial feature among those is to equip robots with a mechanism for teaching …
Collapsed amortized variational inference for switching nonlinear dynamical systems
We propose an efficient inference method for switching nonlinear dynamical systems. The
key idea is to learn an inference network which can be used as a proposal distribution for …
key idea is to learn an inference network which can be used as a proposal distribution for …
Distillation of rl policies with formal guarantees via variational abstraction of markov decision processes
We consider the challenge of policy simplification and verification in the context of policies
learned through reinforcement learning (RL) in continuous environments. In well-behaved …
learned through reinforcement learning (RL) in continuous environments. In well-behaved …
Newtonianvae: Proportional control and goal identification from pixels via physical latent spaces
Learning low-dimensional latent state space dynamics models has proven powerful for
enabling vision-based planning and learning for control. We introduce a latent dynamics …
enabling vision-based planning and learning for control. We introduce a latent dynamics …
[HTML][HTML] Examples of Gibsonian affordances in legged robotics research using an empirical, generative framework
Evidence from empirical literature suggests that explainable complex behaviors can be built
from structured compositions of explainable component behaviors with known properties …
from structured compositions of explainable component behaviors with known properties …
Learning behavioral models by recurrent neural networks with discrete latent representations with application to a flexible industrial conveyor
Recurrent neural networks (RNN) are being extensively exploited in industry to address
complex predictive tasks by leveraging on the increased availability of data from processes …
complex predictive tasks by leveraging on the increased availability of data from processes …
Hierarchical decomposition of nonlinear dynamics and control for system identification and policy distillation
H Abdulsamad, J Peters - Learning for Dynamics and Control, 2020 - proceedings.mlr.press
Control of nonlinear systems with unknown dynamics is a major challenge on the road to
fully autonomous agents. Current trends in reinforcement learning (RL) focus on complex …
fully autonomous agents. Current trends in reinforcement learning (RL) focus on complex …
Hybrid system identification using a mixture of NARX experts with LASSO-based feature selection
The availability of advanced hybrid system identification techniques is fundamental to extract
knowledge in form of models from data streams. Starting from the current state of the art, we …
knowledge in form of models from data streams. Starting from the current state of the art, we …
[HTML][HTML] Efficient and Trustworthy Artificial Intelligence for Critical Robotic Systems
C Sprague - 2022 - diva-portal.org
Critical robotic systems are systems whose functioning is critical to both ensuring the
accomplishment of a given mission and preventing the endangerment of life and the …
accomplishment of a given mission and preventing the endangerment of life and the …
Model-Based Reinforcement Learning via Stochastic Hybrid Models
H Abdulsamad, J Peters - IEEE Open Journal of Control …, 2023 - ieeexplore.ieee.org
Optimal control of general nonlinear systems is a central challenge in automation. Enabled
by powerful function approximators, data-driven approaches to control have recently …
by powerful function approximators, data-driven approaches to control have recently …