1 code implementation • 31 Dec 2023 • Sayantan Auddy, Sebastian Bergner, Justus Piater
In this paper, we perform an exploratory study of the effects of different optimizers, initializers, and network architectures on the continual learning performance of hypernetworks for CLfD.
no code implementations • 29 Dec 2023 • Alejandro Agostini, Justus Piater
In task and motion planning (TAMP), the ambiguity and underdetermination of abstract descriptions used by task planning methods make it difficult to characterize physical constraints needed to successfully execute a task.
no code implementations • 18 Dec 2023 • Jakob Hollenstein, Georg Martius, Justus Piater
Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration.
no code implementations • NeurIPS 2023 • Cansu Sancaktar, Justus Piater, Georg Martius
Our generalized formulation of Regularity as Intrinsic Reward (RaIR) allows us to operationalize it within model-based reinforcement learning.
no code implementations • 4 Nov 2023 • Hector Perez-Villeda, Justus Piater, Matteo Saveriano
While conventional approaches for constrained regression use one kind of basis function, e. g., Gaussian, we exploit Equation Learner Networks to learn a set of analytical expressions and use them as basis functions.
2 code implementations • 1 Aug 2022 • David Peer, Bart Keulen, Sebastian Stabinger, Justus Piater, Antonio Rodríguez-Sánchez
We show empirically that we can therefore train a "vanilla" fully connected network and convolutional neural network -- no skip connections, batch normalization, dropout, or any other architectural tweak -- with 500 layers by simply adding the batch-entropy regularization term to the loss function.
no code implementations • 8 Jun 2022 • Jakob Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater
Many Deep Reinforcement Learning (D-RL) algorithms rely on simple forms of exploration such as the additive action noise often used in continuous control domains.
1 code implementation • 14 Feb 2022 • Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano, Antonio Rodríguez-Sánchez, Justus Piater
We empirically demonstrate the effectiveness of this approach in remembering long sequences of trajectory learning tasks without the need to store any data from past demonstrations.
1 code implementation • 4 Dec 2020 • Alper Ahmetoglu, M. Yunus Seker, Justus Piater, Erhan Oztop, Emre Ugur
We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning.
no code implementations • 29 Oct 2020 • Jakob J. Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater
Sufficient exploration is paramount for the success of a reinforcement learning agent.
no code implementations • 24 Oct 2020 • Jakob J. Hollenstein, Erwan Renaudo, Matteo Saveriano, Justus Piater
Local policy search is performed by most Deep Reinforcement Learning (D-RL) methods, which increases the risk of getting trapped in a local minimum.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 29 Jan 2020 • Sebastian Stabinger, Peer David, Justus Piater, Antonio Rodríguez-Sánchez
Convolutional Neural Networks (CNNs) have become the state of the art method for image classification in the last ten years.
no code implementations • 25 Sep 2019 • Jakob J. Hollenstein, Erwan Renaudo, Justus Piater
Most Deep Reinforcement Learning methods perform local search and therefore are prone to get stuck on non-optimal solutions.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 26 Jan 2018 • Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop, Justus Piater, Florentin Wörgötter
However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.
no code implementations • 28 Jul 2016 • Sebastian Stabinger, Antonio Rodríguez-Sánchez, Justus Piater
We try to determine the progress made by convolutional neural networks over the past 25 years in classifying images into abstractc lasses.
no code implementations • 17 Jun 2016 • Sebastian Stabinger, Antonio Rodriguez-Sanchez, Justus Piater
Humans are generally good at learning abstract concepts about objects and scenes (e. g.\ spatial orientation, relative sizes, etc.).
no code implementations • 25 May 2013 • Justus Piater, Antonio J. Rodríguez Sánchez
In this editorial, the organizers summarize facts and background about the event.
no code implementations • 6 Apr 2013 • Justus Piater, Antonio Rodríguez-Sánchez
This volume represents the proceedings of the 37th Annual Workshop of the Austrian Association for Pattern Recognition (\"OAGM/AAPR), held May 23-24, 2013, in Innsbruck, Austria.
no code implementations • LREC 2012 • Jens Forster, Christoph Schmidt, Thomas Hoyoux, Oscar Koller, Uwe Zelle, Justus Piater, Hermann Ney
This paper introduces the RWTH-PHOENIX-Weather corpus, a video-based, large vocabulary corpus of German Sign Language suitable for statistical sign language recognition and translation.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5