1 citations · 5 across the 9 of their papers we have counts for
12 papers
From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Quentin Bouniot, Ievgen Redko, Anton Mallasto +6
In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explain…
Learning representations that are closed-form Monge mapping optimal with application to domain adaptation
Oliver Struckmeier, Ievgen Redko, Anton Mallasto +3
Optimal transport (OT) is a powerful geometric tool used to compare and align probability measures following the least effort principle. Despite its widespread use in machine learn…
Co-Imitation: Learning Design and Behaviour by Imitation
Chang Rajani, Karol Arndt, David Blanco-Mulero +2
The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evol…
Online vs. Offline Adaptive Domain Randomization Benchmark
Gabriele Tiboni, Karol Arndt, Giuseppe Averta +2
Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowle…
Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models
Ali Ghadirzadeh, Petra Poklukar, Karol Arndt +4
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative m…
SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation
Rituraj Kaushik, Karol Arndt, Ville Kyrki
The framework of Simulation-to-real learning, i.e, learning policies in simulation and transferring those policies to the real world is one of the most promising approaches towards…
DROPO: Sim-to-Real Transfer with Offline Domain Randomization
Gabriele Tiboni, Karol Arndt, Ville Kyrki
In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manip…
Affine Transport for Sim-to-Real Domain Adaptation
Anton Mallasto, Karol Arndt, Markus Heinonen +2
Sample-efficient domain adaptation is an open problem in robotics. In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between st…
Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
Karol Arndt, Oliver Struckmeier, Ville Kyrki
Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation,…
Few-shot model-based adaptation in noisy conditions
Karol Arndt, Ali Ghadirzadeh, Murtaza Hazara +1
Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additio…
Meta Reinforcement Learning for Sim-to-real Domain Adaptation
Karol Arndt, Murtaza Hazara, Ali Ghadirzadeh +1
Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this wo…
Affordance Learning for End-to-End Visuomotor Robot Control
Aleksi Hämäläinen, Karol Arndt, Ali Ghadirzadeh +1
Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide. In this work, we propose to tackle this issu…