no code implementations • 18 Jul 2022 • Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Ali Ghadirzadeh, Danica Kragic
However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time.
no code implementations • 18 Apr 2022 • Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.
1 code implementation • 16 Mar 2022 • Xi Chen, Ali Ghadirzadeh, Tianhe Yu, Yuan Gao, Jianhao Wang, Wenzhe Li, Bin Liang, Chelsea Finn, Chongjie Zhang
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions.
no code implementations • ICLR Workshop Learning_to_Learn 2021 • Ali Ghadirzadeh, Petra Poklukar, Xi Chen, Huaxiu Yao, Hossein Azizpour, Mårten Björkman, Chelsea Finn, Danica Kragic
Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.
no code implementations • 5 Mar 2021 • Ali Ghadirzadeh, Xi Chen, Petra Poklukar, Chelsea Finn, Mårten Björkman, Danica Kragic
Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.
no code implementations • 16 Oct 2020 • Karol Arndt, Ali Ghadirzadeh, Murtaza Hazara, Ville Kyrki
Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection.
no code implementations • 26 Jul 2020 • Ali Ghadirzadeh, Petra Poklukar, Ville Kyrki, Danica Kragic, Mårten Björkman
We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models.
no code implementations • 2 Jul 2020 • Ali Ghadirzadeh, Xi Chen, Wenjie Yin, Zhengrong Yi, Mårten Björkman, Danica Kragic
We present a reinforcement learning based framework for human-centered collaborative systems.
no code implementations • 14 Oct 2019 • Judith Bütepage, Ali Ghadirzadeh, Özge Öztimur Karadag, Mårten Björkman, Danica Kragic
To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals.
no code implementations • 25 Sep 2019 • Xi Chen, Yuan Gao, Ali Ghadirzadeh, Marten Bjorkman, Ginevra Castellano, Patric Jensfelt
In this work, we introduce an exploration approach based on maximizing the entropy of the visited states while learning a goal-conditioned policy.
no code implementations • 17 Sep 2019 • Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt
Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs.
no code implementations • 16 Sep 2019 • Karol Arndt, Murtaza Hazara, Ali Ghadirzadeh, Ville Kyrki
Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware.
2 code implementations • 10 Mar 2019 • Aleksi Hämäläinen, Karol Arndt, Ali Ghadirzadeh, Ville Kyrki
Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide.
no code implementations • 8 Nov 2018 • Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt
Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives.
no code implementations • 27 Apr 2018 • Xi Chen, Ali Ghadirzadeh, John Folkesson, Patric Jensfelt
Mobile robot navigation in complex and dynamic environments is a challenging but important problem.
no code implementations • 27 Jul 2016 • Ali Ghadirzadeh, Judith Bütepage, Atsuto Maki, Danica Kragic, Mårten Björkman
Modeling of physical human-robot collaborations is generally a challenging problem due to the unpredictive nature of human behavior.