AIConfPaper
← Search

Konrad Czechowski

4 accepted papers

2023

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

Michał Zawalski, Michał Tyrolski, Konrad Czechowski, Tomasz Odrzygóźdź, Damian Stachura, Piotr Piękos +3
ICLR 2023top-5%

Complex reasoning problems contain states that vary in the computational cost required to determine the right action plan. To take advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method that adaptively adjusts the planning horizon. To this end, AdaSubS generates di…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2022

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers

Albert Qiaochu Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzygóźdź, Piotr Miłoś +2
NeurIPS 2022accept

In theorem proving, the task of selecting useful premises from a large library to unlock the proof of a given conjecture is crucially important. This presents a challenge for all theorem provers, especially the ones based on language models, due to their relative inability to reason over huge volume…

Cited by 104Source ↗PDF ↗Scholar ↗
2021

Subgoal Search For Complex Reasoning Tasks

Konrad Czechowski, Tomasz Odrzygóźdź, Marek Zbysiński, Michał Zawalski, Krzysztof Olejnik, Yuhuai Wu +2
NeurIPS 2021poster

Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to…

Cited by 27Source ↗PDF ↗code ↗Scholar ↗
2020

Model Based Reinforcement Learning for Atari

Łukasz Kaiser, Mohammad Babaeizadeh, Piotr Miłos, Błażej Osiński, Roy H Campbell, Konrad Czechowski +8
ICLR 2020spotlight

Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How…

Cited by 1127Source ↗code ↗Scholar ↗