Adaptive scale-invariant online algorithms for learning linear models

no code implementations • 20 Feb 2019 • Michał Kempka, Wojciech Kotłowski, Manfred K. Warmuth

We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight.

ViZDoom Competitions: Playing Doom from Pixels

6 code implementations • 10 Sep 2018 • Marek Wydmuch, Michał Kempka, Wojciech Jaśkowski

The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game.

Navigate reinforcement-learning +1

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

9 code implementations • 6 May 2016 • Michał Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek, Wojciech Jaśkowski

Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world.

Atari Games Game of Doom +3