Regularizing model-based planning with energy-based models R Boney, J Kannala, A Ilin Conference on Robot Learning, 182-191, 2020 | 56 | 2020 |
Recurrent ladder networks I Prémont-Schwarz, A Ilin, T Hao, A Rasmus, R Boney, H Valpola Advances in neural information processing systems 30, 2017 | 41 | 2017 |
Semi-supervised few-shot learning with prototypical networks R Boney, A Ilin CoRR abs/1711.10856, 2017 | 34 | 2017 |
Adaptive behavior cloning regularization for stable offline-to-online reinforcement learning Y Zhao, R Boney, A Ilin, J Kannala, J Pajarinen arXiv preprint arXiv:2210.13846, 2022 | 31 | 2022 |
Semi-supervised few-shot learning with MAML R Boney, A Ilin | 30 | 2018 |
Semi-supervised and active few-shot learning with prototypical networks R Boney, A Ilin arXiv preprint arXiv:1711.10856, 2017 | 25 | 2017 |
Regularizing trajectory optimization with denoising autoencoders R Boney, N Di Palo, M Berglund, A Ilin, J Kannala, A Rasmus, H Valpola Advances in Neural Information Processing Systems 32, 2019 | 15 | 2019 |
Learning to drive small scale cars from scratch A Viitala, R Boney, J Kannala arXiv preprint arXiv:2008.00715, 2020 | 14* | 2020 |
Recurrent ladder networks A Ilin, I Prémont-Schwarz, TH Hao, A Rasmus, R Boney, H Valpola arXiv preprint arXiv:1707.09219 3 (6), 2017 | 11 | 2017 |
Simplified temporal consistency reinforcement learning Y Zhao, W Zhao, R Boney, J Kannala, J Pajarinen International Conference on Machine Learning, 42227-42246, 2023 | 10 | 2023 |
Sacplanner: Real-world collision avoidance with a soft actor critic local planner and polar state representations K Nakhleh, M Raza, M Tang, M Andrews, R Boney, I Hadžić, J Lee, ... 2023 IEEE International Conference on Robotics and Automation (ICRA), 9464-9470, 2023 | 9 | 2023 |
Understanding alignment in multimodal llms: A comprehensive study E Amirloo, JP Fauconnier, C Roesmann, C Kerl, R Boney, Y Qian, Z Wang, ... arXiv preprint arXiv:2407.02477, 2024 | 8 | 2024 |
RealAnt: An Open-Source Low-Cost Quadruped for Education and Research in Real-World Reinforcement Learning R Boney, J Sainio, M Kaivola, A Solin, J Kannala arXiv preprint arXiv:2011.03085, 2020 | 8 | 2020 |
Active one-shot learning with prototypical networks R Boney, A Ilin European Symposium on Artificial Neural Networks, Computational Intelligence …, 2019 | 7 | 2019 |
Learning of feature points without additional supervision improves reinforcement learning from images R Boney, A Ilin, J Kannala arXiv preprint arXiv:2106.07995, 2021 | 5* | 2021 |
Learning to play imperfect-information games by imitating an oracle planner R Boney, A Ilin, J Kannala, J Seppänen IEEE Transactions on Games 14 (2), 262-272, 2021 | 4 | 2021 |
Sample-Efficient Methods for Real-World Deep Reinforcement Learning R Boney Aalto University, 2022 | | 2022 |
Fast Adaptation of Neural Networks R Boney | | 2018 |