Projects funded by the NCN

Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Reinforcement learning - contemporary challenges

2017/26/E/ST6/00622

Keywords:

machine learning reinforcement learning artificial intelligence

Descriptors:

  • ST6_7: Artificial intelligence, intelligent systems, multi-agent systems

Panel:

ST6 - Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution :

Uniwersytet Warszawski, Wydział Matematyki, Informatyki i Mechaniki

woj. mazowieckie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr Piotr Miłoś 

Number of co-investigators in the project: 5

Call: SONATA BIS 7 - announced on 2017-06-14

Amount awarded: 1 746 300 PLN

Project start date (Y-m-d): 2018-04-20

Project end date (Y-m-d): 2023-04-19

Project duration:: 60 months (the same as in the proposal)

Project status: Project settled

Project description

Download the project description in a pdf file

Note - project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Equipment purchased [PL]

  1. Laptops (40 000 PLN)
  2. Komputery z GPU (300 000 PLN)

Information in the final report

  • Articles in post-conference publications (6)
  1. Simulation-based reinforcement learning for real-world autonomous driving
    Authors:
    Błażej Osiński, Adam Jakubowski, Paweł Zięcina, Piotr Miłoś, Christopher Galias, Silviu Homoceanu, Henryk Michalewski
    Conference:
    International Conference on Robotics and Automation (rok: 2020, ), Wydawca: IEEE
    Data:
    konferencja 43982
    Status:
    Published
  2. Continual World: A Robotic Benchmark For Continual Reinforcement Learning
    Authors:
    Maciej Wołczyk, Michał Zając, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś
    Conference:
    Neural Information Processing Systems (rok: 2021, ), Wydawca: Curran Associates, Inc
    Data:
    konferencja 12,2021
    Status:
    Published
    DOI:
    link to the publication
  3. Model Based Reinforcement Learning for Atari
    Authors:
    Łukasz Kaiser, Mohammad Babaeizadeh, Piotr Miłoś, Błażej Osiński, Roy H. Campbell, Konrad Czechowski, Dumitru Erhan, Chelsea Finn, Piotr Kozakowski, Sergey Levine, Afroz Mohiuddin, Ryan Sepassi, George Tucker, Henryk Michalewski
    Conference:
    International Conference on Learning Representations (rok: 2020, ), Wydawca: electronic
    Data:
    konferencja 43947
    Status:
    Published
  4. Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
    Authors:
    Łukasz Kuciński, Tomasz Korbak, Paweł Kołodziej, Piotr Miłoś
    Conference:
    Neural Information Processing Systems (rok: 2021, ), Wydawca: Curran Associates, Inc
    Data:
    konferencja 12,2021
    Status:
    Published
    DOI:
    link to the publication
  5. Structure and randomness in planning and reinforcement learning
    Authors:
    Piotr Januszewski, Konrad Czechowski, Piotr Kozakowski, Łukasz Kuciński, Piotr Miłoś
    Conference:
    IJCNN (rok: 2021, ), Wydawca: IEEE
    Data:
    konferencja 7,2021
    Status:
    Published
  6. Subgoal Search For Complex Reasoning Tasks
    Authors:
    Konrad Czechowski, Tomasz Odrzygóźdź, Marek Zbysiński, Michał Zawalski, Krzysztof Olejnik, Yuhuai Wu, Łukasz Kuciński, Piotr Miłoś
    Conference:
    Neural Information Processing Systems (rok: 2021, ), Wydawca: Curran Associates, Inc
    Data:
    konferencja 12,2021
    Status:
    Published
    DOI:
    link to the publication

O Narodowym Centrum Nauki

Finansowanie nauki

Współpraca zagraniczna

Centrum prasowe

Deklaracja dostępności
Przetwarzanie danych osobowych
Polityka cookies

Partnerzy