publications.bib

@article{doncieux2021learning,
  author = {Stephane Doncieux},
  title = {Apprendre aux robots à faire face à l'imprévu},
  journal = {Industries et Technologies},
  volume = {1045},
  note = {Cahier Technique},
  year = {2021}
}
@article{raffin2021fault,
  title = {Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms},
  author = {Raffin, Antonin and Deutschmann, Bastian and Stulp, Freek},
  journal = {Frontiers in Robotics and AI},
  volume = {8},
  pages = {11},
  year = {2021},
  url = {https://www.frontiersin.org/articles/10.3389/frobt.2021.619238/abstract},
  publisher = {Frontiers},
  abstract = {We propose a fault-tolerant estimation technique for the six-DoF pose of a tendon-driven continuum mechanisms using machine learning. In contrast to previous estimation techniques, no deformation model is required, and the pose prediction is rather performed with polynomial regression. As only a few datapoints are required for the regression, several estimators are trained with structured occlusions of the available sensor information, and clustered into ensembles based on the available sensors. By computing the variance of one ensemble, the uncertainty in the prediction is monitored and, if the variance is above a threshold, sensor loss is detected and handled. Experiments on the humanoid neck of the DLR robot DAVID, demonstrate that the accuracy of the predicted pose is significantly improved, and a reliable prediction can still be performed using only 3 out of 8 sensors.}
}
@inbook{salehi21brns,
  author = {Salehi, Achkan and Coninx, Alexandre and Doncieux, Stephane},
  title = {BR-NS: An Archive-Less Approach to Novelty Search},
  year = {2021},
  isbn = {9781450383509},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3449639.3459303},
  abstract = {As open-ended learning based on divergent search algorithms such as Novelty Search
(NS) draws more and more attention from the research community, it is natural to expect
that its application to increasingly complex real-world problems will require the
exploration to operate in higher dimensional Behavior Spaces (BSs) which will not
necessarily be Euclidean. Novelty Search traditionally relies on k-nearest neighbours
search and an archive of previously visited behavior descriptors which are assumed
to live in a Euclidean space. This is problematic because of a number of issues. On
one hand, Euclidean distance and Nearest-neighbour search are known to behave differently
and become less meaningful in high dimensional spaces. On the other hand, the archive
has to be bounded since, memory considerations aside, the computational complexity
of finding nearest neighbours in that archive grows linearithmically with its size.
A sub-optimal bound can result in "cycling" in the behavior space, which inhibits
the progress of the exploration. Furthermore, the performance of NS depends on a number
of algorithmic choices and hyperparameters, such as the strategies to add or remove
elements to the archive and the number of neighbours to use in k-nn search. In this
paper, we discuss an alternative approach to novelty estimation, dubbed Behavior Recognition
based Novelty Search (BR-NS), which does not require an archive, makes no assumption
on the metrics that can be defined in the behavior space and does not rely on nearest
neighbours search. We conduct experiments to gain insight into its feasibility and
dynamics as well as potential advantages over archive-based NS in terms of time complexity.},
  booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference},
  pages = {172–179},
  numpages = {8}
}
@inproceedings{raffin2021smooth,
  author = {Antonin Raffin and Jens Kober and Freek Stulp},
  title = {Smooth Exploration for Robotic Reinforcement Learning},
  booktitle = {Conference on Robot Learning},
  year = {2021}
}
@article{raffin2021sb3,
  title = {Stable-Baselines3: Reliable Reinforcement Learning Implementations},
  author = {Raffin, Antonin and Hill, Ashley and Gleave, Adam and Kanervisto, Anssi and Dormann, Noah},
  journal = {Journal of Machine Learning Research},
  year = {2021},
  abstract = {Stable-Baselines3 provides open-source implementations of deep reinforcement learning (RL) algorithms in Python.
The implementations have been benchmarked against reference codebases, and automated unit tests cover 95% of the code.
The algorithms follow a consistent interface and are accompanied by extensive documentation, making it simple to train and compare different RL algorithms.
Our documentation, examples, and source-code are available at https://github.com/DLR-RM/stable-baselines3}
}

This file was generated by bibtex2html 1.99.