Jan Humplik
Jan Humplik
Research Scientist, DeepMind
Verified email at
Cited by
Cited by
Meta reinforcement learning as task inference
J Humplik, A Galashov, L Hasenclever, PA Ortega, YW Teh, N Heess
arXiv preprint arXiv:1905.06424, 2019
Probabilistic models for neural populations that naturally capture global coupling and criticality
J Humplik, G Tkačik
PLoS computational biology 13 (9), e1005763, 2017
Evolutionary dynamics of infectious diseases in finite populations
J Humplik, AL Hill, MA Nowak
Journal of theoretical biology 360, 149-162, 2014
Neural belief states for partially observed domains
P Moreno, J Humplik, G Papamakarios, BA Pires, L Buesing, N Heess, ...
NeurIPS 2018 workshop on reinforcement learning under partial observability, 2018
Towards real robot learning in the wild: A case study in bipedal locomotion
M Bloesch, J Humplik, V Patraucean, R Hafner, T Haarnoja, A Byravan, ...
Conference on Robot Learning, 1502-1511, 2022
Imitate and repurpose: Learning reusable robot movement skills from human and animal behaviors
S Bohez, S Tunyasuvunakool, P Brakel, F Sadeghi, L Hasenclever, ...
arXiv preprint arXiv:2203.17138, 2022
Inferring couplings in networks across order-disorder phase transitions
V Ngampruetikorn, V Sachdeva, J Torrence, J Humplik, DJ Schwab, ...
Physical Review Research 4 (2), 023240, 2022
Semiparametric energy-based probabilistic models
J Humplik, G Tkačik
arXiv preprint arXiv:1605.07371, 2016
Nerf2real: Sim2real transfer of vision-guided bipedal motion skills using neural radiance fields
A Byravan, J Humplik, L Hasenclever, A Brussee, F Nori, T Haarnoja, ...
arXiv preprint arXiv:2210.04932, 2022
Importance weighted policy learning and adaptation
A Galashov, J Sygnowski, G Desjardins, J Humplik, L Hasenclever, ...
arXiv preprint arXiv:2009.04875, 2020
Learning agile soccer skills for a bipedal robot with deep reinforcement learning
T Haarnoja, B Moran, G Lever, SH Huang, D Tirumala, M Wulfmeier, ...
arXiv preprint arXiv:2304.13653, 2023
Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data
W Zhou, S Bohez, J Humplik, N Heess, A Abdolmaleki, D Rao, ...
Conference on Lifelong Learning Agents, 294-309, 2022
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
G Vezzani, D Tirumala, M Wulfmeier, D Rao, A Abdolmaleki, B Moran, ...
arXiv preprint arXiv:2211.13743, 2022
Offline Distillation for Robot Lifelong Learning with Imbalanced Experience
W Zhou, S Bohez, J Humplik, A Abdolmaleki, D Rao, M Wulfmeier, ...
arXiv preprint arXiv:2204.05893, 2022
Semiparametric energy-based models of systems exhibiting criticality
J Humplik, G Tkacik
APS March Meeting Abstracts 2016, F41. 002, 2016
The system can't perform the operation now. Try again later.
Articles 1–15