Piotr Milos

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 49

Top Topics

Automated Theorem Provers

Data Representations

Reasoning Tasks

Reinforcement Learning

Top Venues

Publications

Michal Nauman, Mateusz Ostaszewski, Krzysztof Jankowski, Piotr Milos, Marek Cygan
Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control. CoRR (2024)
Michal Nauman, Michal Bortkiewicz, Mateusz Ostaszewski, Piotr Milos, Tomasz Trzcinski, Marek Cygan
Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning. CoRR (2024)
Alicja Ziarko, Albert Q. Jiang, Bartosz Piotrowski, Wenda Li, Mateja Jamnik, Piotr Milos
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe. CoRR (2024)
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Milos, Yuxiang Wu, Pasquale Minervini
Analysing The Impact of Sequence Composition on Language Model Pre-Training. CoRR (2024)
Michal Zawalski, Gracjan Góral, Michal Tyrolski, Emilia Wisnios, Franciszek Budrowski, Lukasz Kucinski, Piotr Milos
What Matters in Hierarchical Search for Combinatorial Reasoning Problems? CoRR (2024)
Maciej Mikula, Szymon Tworkowski, Szymon Antoniak, Bartosz Piotrowski, Albert Q. Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu
Magnushammer: A Transformer-Based Approach to Premise Selection. ICLR (2024)
Yu Zhao, Yuanbin Qu, Konrad Staniszewski, Szymon Tworkowski, Wei Liu, Piotr Milos, Yuxiang Wu, Pasquale Minervini
Analysing The Impact of Sequence Composition on Language Model Pre-Training. ACL (1) (2024)
Maciej Wolczyk, Bartlomiej Cupial, Mateusz Ostaszewski, Michal Bortkiewicz, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem. CoRR (2024)
Lukasz Kucinski, Witold Drzewakowski, Mateusz Olko, Piotr Kozakowski, Lukasz Maziarka, Marta Emilia Nowakowska, Lukasz Kaiser, Piotr Milos
tsGT: Stochastic Time Series Modeling With Transformer. CoRR (2024)
Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur, Henryk Michalewski, Lukasz Kucinski, Piotr Milos
Structured Packing in LLM Training Improves Long Context Utilization. CoRR (2023)
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Milos, Tomasz Trzcinski
The Tunnel Effect: Building Data Representations in Deep Neural Networks. NeurIPS (2023)
Szymon Tworkowski, Konrad Staniszewski, Mikolaj Pacek, Yuhuai Wu, Henryk Michalewski, Piotr Milos
Focused Transformer: Contrastive Training for Context Scaling. CoRR (2023)
Szymon Tworkowski, Konrad Staniszewski, Mikolaj Pacek, Yuhuai Wu, Henryk Michalewski, Piotr Milos
Focused Transformer: Contrastive Training for Context Scaling. NeurIPS (2023)
Michal Zajac, Kamil Deja, Anna Kuzina, Jakub M. Tomczak, Tomasz Trzcinski, Florian Shkurti, Piotr Milos
Exploring Continual Learning of Diffusion Models. CoRR (2023)
Michal Zawalski, Michal Tyrolski, Konrad Czechowski, Tomasz Odrzygózdz, Damian Stachura, Piotr Piekos, Yuhuai Wu, Lukasz Kucinski, Piotr Milos
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search. ICLR (2023)
Maciej Mikula, Szymon Antoniak, Szymon Tworkowski, Albert Qiaochu Jiang, Jin Peng Zhou, Christian Szegedy, Lukasz Kucinski, Piotr Milos, Yuhuai Wu
Magnushammer: A Transformer-based Approach to Premise Selection. CoRR (2023)
Mateusz Olko, Michal Zajac, Aleksandra Nowak, Nino Scherrer, Yashas Annadani, Stefan Bauer, Lukasz Kucinski, Piotr Milos
Trust Your 𝛁: Gradient-based Intervention Targeting for Causal Discovery. NeurIPS (2023)
Samuel Kessler, Mateusz Ostaszewski, Michal Pawel Bortkiewicz, Mateusz Zarski, Maciej Wolczyk, Jack Parker-Holder, Stephen J. Roberts, Piotr Milos
The Effectiveness of World Models for Continual Reinforcement Learning. CoLLAs (2023)
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Milos, Tomasz Trzcinski
The Tunnel Effect: Building Data Representations in Deep Neural Networks. CoRR (2023)
Albert Qiaochu Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygózdz, Piotr Milos, Yuhuai Wu, Mateja Jamnik
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers. NeurIPS (2022)
Piotr Kozakowski, Mikolaj Pacek, Piotr Milos
Planning and Learning using Adaptive Entropy Tree Search. IJCNN (2022)
Michal Zawalski, Blazej Osinski, Henryk Michalewski, Piotr Milos
Off-Policy Correction For Multi-Agent Reinforcement Learning. AAMAS (2022)
Samuel Kessler, Piotr Milos, Jack Parker-Holder, Stephen J. Roberts
The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning. CoRR (2022)
Mateusz Olko, Michal Zajac, Aleksandra Nowak, Nino Scherrer, Yashas Annadani, Stefan Bauer, Lukasz Kucinski, Piotr Milos
Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery. CoRR (2022)
Albert Q. Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygózdz, Piotr Milos, Yuhuai Wu, Mateja Jamnik
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers. CoRR (2022)
Michal Zawalski, Michal Tyrolski, Konrad Czechowski, Damian Stachura, Piotr Piekos, Tomasz Odrzygózdz, Yuhuai Wu, Lukasz Kucinski, Piotr Milos
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search. CoRR (2022)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Disentangling Transfer in Continual Reinforcement Learning. CoRR (2022)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Disentangling Transfer in Continual Reinforcement Learning. NeurIPS (2022)
Lukasz Kucinski, Tomasz Korbak, Pawel Kolodziej, Piotr Milos
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication. NeurIPS (2021)
Konrad Czechowski, Piotr Januszewski, Piotr Kozakowski, Lukasz Kucinski, Piotr Milos
Structure and Randomness in Planning and Reinforcement Learning. IJCNN (2021)
Konrad Czechowski, Tomasz Odrzygózdz, Marek Zbysinski, Michal Zawalski, Krzysztof Olejnik, Yuhuai Wu, Lukasz Kucinski, Piotr Milos
Subgoal Search For Complex Reasoning Tasks. NeurIPS (2021)
Piotr Januszewski, Mateusz Olko, Michal Królikowski, Jakub Swiatkowski, Marcin Andrychowicz, Lukasz Kucinski, Piotr Milos
Continuous Control With Ensemble Deep Deterministic Policy Gradients. CoRR (2021)
Lukasz Kucinski, Tomasz Korbak, Pawel Kolodziej, Piotr Milos
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication. CoRR (2021)
Michal Zawalski, Blazej Osinski, Henryk Michalewski, Piotr Milos
Off-Policy Correction For Multi-Agent Reinforcement Learning. CoRR (2021)
Konrad Czechowski, Tomasz Odrzygózdz, Marek Zbysinski, Michal Zawalski, Krzysztof Olejnik, Yuhuai Wu, Lukasz Kucinski, Piotr Milos
Subgoal Search For Complex Reasoning Tasks. CoRR (2021)
Piotr Kozakowski, Mikolaj Pacek, Piotr Milos
Robust and Efficient Planning using Adaptive Entropy Tree Search. CoRR (2021)
Konrad Czechowski, Tomasz Odrzygózdz, Michal Izworski, Marek Zbysinski, Lukasz Kucinski, Piotr Milos
Trust, but Verify: Alleviating Pessimistic Errors in Model-Based Exploration. IJCNN (2021)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Continual World: A Robotic Benchmark For Continual Reinforcement Learning. NeurIPS (2021)
Maciej Wolczyk, Michal Zajac, Razvan Pascanu, Lukasz Kucinski, Piotr Milos
Continual World: A Robotic Benchmark For Continual Reinforcement Learning. CoRR (2021)
Blazej Osinski, Adam Jakubowski, Pawel Ziecina, Piotr Milos, Christopher Galias, Silviu Homoceanu, Henryk Michalewski
Simulation-Based Reinforcement Learning for Real-World Autonomous Driving. ICRA (2020)
Lukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos, Blazej Osinski, Roy H. Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker, Henryk Michalewski
Model Based Reinforcement Learning for Atari. ICLR (2020)
Blazej Osinski, Piotr Milos, Adam Jakubowski, Pawel Ziecina, Michal Martyniak, Christopher Galias, Antonia Breuer, Silviu Homoceanu, Henryk Michalewski
CARLA Real Traffic Scenarios - novel training ground and benchmark for autonomous driving. CoRR (2020)
Lukasz Kaiser, Mohammad Babaeizadeh, Piotr Milos, Blazej Osinski, Roy H. Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Ryan Sepassi, George Tucker, Henryk Michalewski
Model-Based Reinforcement Learning for Atari. CoRR (2019)
Blazej Osinski, Adam Jakubowski, Piotr Milos, Pawel Ziecina, Christopher Galias, Silviu Homoceanu, Henryk Michalewski
Simulation-based reinforcement learning for real-world autonomous driving. CoRR (2019)
Piotr Milos, Lukasz Kucinski, Konrad Czechowski, Piotr Kozakowski, Maciej Klimek
Uncertainty-sensitive Learning and Planning with Ensembles. CoRR (2019)
Tomasz Korbak, Julian Zubek, Lukasz Kucinski, Piotr Milos, Joanna Raczaszek-Leonardi
Developmentally motivated emergence of compositional communication via template transfer. CoRR (2019)
Michal Garmulewicz, Henryk Michalewski, Piotr Milos
Expert-augmented actor-critic for ViZDoom and Montezumas Revenge. CoRR (2018)
Lukasz Kidzinski, Sharada Prasanna Mohanty, Carmichael F. Ong, Zhewei Huang, Shuchang Zhou, Anton Pechenko, Adam Stelmaszczyk, Piotr Jarosik, Mikhail Pavlov, Sergey Kolesnikov, Sergey M. Plis, Zhibo Chen, Zhizheng Zhang, Jiale Chen, Jun Shi, Zhuobin Zheng, Chun Yuan, Zhihui Lin, Henryk Michalewski, Piotr Milos, Blazej Osinski, Andrew Melnik, Malte Schilling, Helge J. Ritter, Sean F. Carroll, Jennifer L. Hicks, Sergey Levine, Marcel Salathé, Scott L. Delp
Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments. CoRR (2018)
Maciej Klimek, Henryk Michalewski, Piotr Milos
Hierarchical Reinforcement Learning with Parameters. CoRL (2017)