About me
I’m a post-doc at IDEAS NCBR under supervision of Prof. Piotr Miłoś. I’m interested in:
- Sequential Decision Making – how to use models such as RNNs, transformers, and state-space models in RL and beyond.
- Reinforcement Learning – how to increase the sample efficiency and leverage models pre-trained on offline data.
- Continual Learning – how to remember the past and reuse it efficiently when learning from a stream of data.
- Generative Models – how to perform weakly supervised conditional generation and adapt existing models for conditional generation.
News
- (February 2024) Our paper on the issue of forgetting in RL fine-tuning is out! Also, check out this talk given by Bartek, my amazing co-author.
- (February 2024) I defended my PhD thesis with distinction! Huge thanks to my supervisor, prof. Jacek Tabor and everyone who helped me along the way.
- (January 2024) A work on compositional generalization and modularity I helped with was accepted at ICLR 2024. Congrats to the whole team!
- (October 2023) Started work as a research engineer at IDEAS NCBR! Hopefully, the job title will change to “post-doc” soon :)
- (June 2023) Submitted my PhD thesis, awaiting reviews! Went on a break to recharge my batteries.
- (June 2023) Our paper on world models in continual reinforcement learning was accepted to CoLLAs 2023.
- (January 2023) I had the chance to present my work on continual reinforcement learning at the Warsaw.ai meetup.
- (November 2022) I will be at NeurIPS to present our work on Disentangling Transfer in Continual Reinforcement Learning. If you’ll also be there and you want to grab a coffee together, send me an e-mail or a Twitter DM!
- (July 2022) MLSS^N was terrific! Many thanks to all lecturers, co-organizers and participants. Check out the lectures!
- (May 2022) Our paper on continual learning with weight interval regularization has been accepted to ICML 2022 as a short presentation.
- (March 2022) Our workshop on Dynamic Neural Networks has been accepted to ICML 2022. See you in Baltimore!
- (March 2022) Started a research internship with João Sacramento at ETH Zurich!
- (December 2021) PluGeN, our paper on introducing supervision to pre-trained, was accepted to AAAI 2022.
- (September 2021) Two of our papers, Zero Time Waste and Continual World were accepted to the NeurIPS 2021 conference as poster presentations.
- (September 2021) A paper on closed-loop imitation learning for self-driving cars, which I worked on during my internship at Woven Planet, was accepted to CORL 2021 conference.
- (April 2021) Started my internship at Woven Planet Level-5 (previously Lyft Level-5), working on imitation learning for planning in self-driving cars.
- (August 2020) Our paper on conditional semi-supervised generation with mixtures of Gaussians was published in IEEE Transactions on Neural Networks and Learning Systems.
- (July 2020) Co-organized the EEML 2020 summer school.
Selected publications
Disentangling Transfer in Continual Reinforcement Learning
Maciej Wołczyk*, Michał Zając*, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś
NeurIPS 2022
[Paper]
Maciej Wołczyk*, Michał Zając*, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś
NeurIPS 2022
[Paper]