Piotr Januszewski - Publications - Bridge of Knowledge

Search

Filters

total: 4

  • Category
  • Year
  • Options

clear Chosen catalog filters disabled

Catalog Publications

  • Dataset Characteristics and Their Impact on Offline Policy Learning of Contextual Multi-Armed Bandits
    Publication

    The Contextual Multi-Armed Bandits (CMAB) framework is pivotal for learning to make decisions. However, due to challenges in deploying online algorithms, there is a shift towards offline policy learning, which relies on pre-existing datasets. This study examines the relationship between the quality of these datasets and the performance of offline policy learning algorithms, specifically, Neural Greedy and NeuraLCB. Our results...

    Full text available to download

  • Model-free and Model-based Reinforcement Learning, the Intersection of Learning and Planning
    Publication

    - Year 2022

    My doctoral dissertation is intended as the compound of four publications considering: structure and randomness in planning and reinforcement learning, continuous control with ensemble deep deterministic policy gradients, toddler-inspired active representation learning, and large-scale deep reinforcement learning costs.

    Full text to download in external service

  • Rola i techniki eksploracji w uczeniu przez wzmacnianie
    Publication

    - Year 2021

    W rozdziale podjęto rozważania na temat roli eksploracji w uczeniu się agentów sztucznej inteligencji przez wzmacnianie. Prezentuje przegląd współczesnych technik eksploracji i rozróżnia dwie główne rodziny technik: eksplorację nieukierunkowaną i eksplorację ukierunkowaną. Praca ta powinna pomóc zrozumieć dylemat pomiędzy eksploatacją wiedzy a eksploracją środowiska, któremu poddany jest agent w każdym kroku interakcji ze środowiskiem....

    Full text to download in external service

  • Structure and Randomness in Planning and Reinforcement Learning
    Publication

    - Year 2021

    Planning in large state spaces inevitably needs to balance the depth and breadth of the search. It has a crucial impact on the performance of a planner and most manage this interplay implicitly. We present a novel method \textit{Shoot Tree Search (STS)}, which makes it possible to control this trade-off more explicitly. Our algorithm can be understood as an interpolation between two celebrated search mechanisms: MCTS and random...

    Full text to download in external service

seen 290 times