Search Results for author: Johannes A. Stork

Found 12 papers, 2 papers with code

Learning Solutions of Stochastic Optimization Problems with Bayesian Neural Networks

1 code implementation5 Jun 2024 Alan A. Lahoud, Erik Schaffernicht, Johannes A. Stork

We propose a novel framework that models prediction uncertainty with Bayesian Neural Networks (BNNs) and propagates this uncertainty into the mathematical solver with a Stochastic Programming technique.

Stochastic Optimization

DataSP: A Differential All-to-All Shortest Path Algorithm for Learning Costs and Predicting Paths with Context

1 code implementation8 May 2024 Alan A. Lahoud, Erik Schaffernicht, Johannes A. Stork

Learning latent costs of transitions on graphs from trajectories demonstrations under various contextual features is challenging but useful for path planning.

Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies

no code implementations2 May 2024 Finn Rietz, Erik Schaffernicht, Stefan Heinrich, Johannes A. Stork

Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains.

reinforcement-learning Reinforcement Learning

Towards Task-Prioritized Policy Composition

no code implementations20 Sep 2022 Finn Rietz, Erik Schaffernicht, Todor Stoyanov, Johannes A. Stork

Combining learned policies in a prioritized, ordered manner is desirable because it allows for modular design and facilitates data reuse through knowledge transfer.

reinforcement-learning Reinforcement Learning +2

Transferring Knowledge for Reinforcement Learning in Contact-Rich Manipulation

no code implementations19 Sep 2022 Quantao Yang, Johannes A. Stork, Todor Stoyanov

We propose to learn prior distribution over the specific skill required to accomplish each task and compose the family of skill priors to guide learning the policy for a new task by comparing the similarity between the target task and the prior ones.

reinforcement-learning Reinforcement Learning +1

The effect of Target Normalization and Momentum on Dying ReLU

no code implementations13 May 2020 Isac Arnekvist, J. Frederico Carvalho, Danica Kragic, Johannes A. Stork

To further investigate this matter, we analyze a discrete-time linear autonomous system, and show theoretically how this relates to a model with a single ReLU and how common properties can result in dying ReLU.

Ensemble of Sparse Gaussian Process Experts for Implicit Surface Mapping with Streaming Data

no code implementations12 Feb 2020 Johannes A. Stork, Todor Stoyanov

In this paper, we learn a compact and continuous implicit surface map of an environment from a stream of range data with known poses.

Global Search with Bernoulli Alternation Kernel for Task-oriented Grasping Informed by Simulation

no code implementations10 Oct 2018 Rika Antonova, Mia Kokic, Johannes A. Stork, Danica Kragic

Our further contribution is a neural network architecture and training pipeline that use experience from grasping objects in simulation to learn grasp stability scores.

Bayesian Optimization

VPE: Variational Policy Embedding for Transfer Reinforcement Learning

no code implementations10 Sep 2018 Isac Arnekvist, Danica Kragic, Johannes A. Stork

The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments.

reinforcement-learning Reinforcement Learning +2

Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning

no code implementations15 Mar 2018 Weihao Yuan, Johannes A. Stork, Danica Kragic, Michael Y. Wang, Kaiyu Hang

Usually, this is achieved by precisely modeling physical properties of the objects, robot, and the environment for explicit planning.

reinforcement-learning Reinforcement Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.