Alert button
Picture for Karol Arndt

Karol Arndt

Alert button

Understanding deep neural networks through the lens of their non-linearity

Oct 17, 2023
Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Karol Arndt, Oliver Struckmeier, Markus Heinonen, Ville Kyrki, Samuel Kaski

Figure 1 for Understanding deep neural networks through the lens of their non-linearity
Figure 2 for Understanding deep neural networks through the lens of their non-linearity
Figure 3 for Understanding deep neural networks through the lens of their non-linearity
Figure 4 for Understanding deep neural networks through the lens of their non-linearity
Viaarxiv icon

Beyond invariant representation learning: linearly alignable latent spaces for efficient closed-form domain adaptation

May 12, 2023
Oliver Struckmeier, Ievgen Redko, Anton Mallasto, Karol Arndt, Markus Heinonen, Ville Kyrki

Figure 1 for Beyond invariant representation learning: linearly alignable latent spaces for efficient closed-form domain adaptation
Figure 2 for Beyond invariant representation learning: linearly alignable latent spaces for efficient closed-form domain adaptation
Figure 3 for Beyond invariant representation learning: linearly alignable latent spaces for efficient closed-form domain adaptation
Figure 4 for Beyond invariant representation learning: linearly alignable latent spaces for efficient closed-form domain adaptation
Viaarxiv icon

Co-Imitation: Learning Design and Behaviour by Imitation

Sep 02, 2022
Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck, Ville Kyrki

Figure 1 for Co-Imitation: Learning Design and Behaviour by Imitation
Figure 2 for Co-Imitation: Learning Design and Behaviour by Imitation
Figure 3 for Co-Imitation: Learning Design and Behaviour by Imitation
Figure 4 for Co-Imitation: Learning Design and Behaviour by Imitation
Viaarxiv icon

Online vs. Offline Adaptive Domain Randomization Benchmark

Jun 29, 2022
Gabriele Tiboni, Karol Arndt, Giuseppe Averta, Ville Kyrki, Tatiana Tommasi

Figure 1 for Online vs. Offline Adaptive Domain Randomization Benchmark
Figure 2 for Online vs. Offline Adaptive Domain Randomization Benchmark
Figure 3 for Online vs. Offline Adaptive Domain Randomization Benchmark
Figure 4 for Online vs. Offline Adaptive Domain Randomization Benchmark
Viaarxiv icon

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

Apr 18, 2022
Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman

Figure 1 for Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
Figure 2 for Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
Figure 3 for Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
Figure 4 for Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
Viaarxiv icon

SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation

Jan 27, 2022
Rituraj Kaushik, Karol Arndt, Ville Kyrki

Figure 1 for SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation
Figure 2 for SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation
Figure 3 for SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation
Figure 4 for SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation
Viaarxiv icon

DROPO: Sim-to-Real Transfer with Offline Domain Randomization

Jan 20, 2022
Gabriele Tiboni, Karol Arndt, Ville Kyrki

Figure 1 for DROPO: Sim-to-Real Transfer with Offline Domain Randomization
Figure 2 for DROPO: Sim-to-Real Transfer with Offline Domain Randomization
Figure 3 for DROPO: Sim-to-Real Transfer with Offline Domain Randomization
Figure 4 for DROPO: Sim-to-Real Transfer with Offline Domain Randomization
Viaarxiv icon

Affine Transport for Sim-to-Real Domain Adaptation

May 25, 2021
Anton Mallasto, Karol Arndt, Markus Heinonen, Samuel Kaski, Ville Kyrki

Figure 1 for Affine Transport for Sim-to-Real Domain Adaptation
Figure 2 for Affine Transport for Sim-to-Real Domain Adaptation
Figure 3 for Affine Transport for Sim-to-Real Domain Adaptation
Figure 4 for Affine Transport for Sim-to-Real Domain Adaptation
Viaarxiv icon

Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

Mar 12, 2021
Karol Arndt, Oliver Struckmeier, Ville Kyrki

Figure 1 for Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
Figure 2 for Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
Figure 3 for Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
Figure 4 for Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
Viaarxiv icon

Few-shot model-based adaptation in noisy conditions

Oct 16, 2020
Karol Arndt, Ali Ghadirzadeh, Murtaza Hazara, Ville Kyrki

Figure 1 for Few-shot model-based adaptation in noisy conditions
Figure 2 for Few-shot model-based adaptation in noisy conditions
Figure 3 for Few-shot model-based adaptation in noisy conditions
Figure 4 for Few-shot model-based adaptation in noisy conditions
Viaarxiv icon