1 citations · 3 across the 4 of their papers we have counts for
7 papers
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…
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…