Improving Hearthstone AI by Combining MCTS and Supervised Learning Algorithms

no code implementations • 14 Aug 2018 • Maciej Świechowski, Tomasz Tajmajer, Andrzej Janusz

We investigate the impact of supervised prediction models on the strength and efficiency of artificial agents that use the Monte-Carlo Tree Search (MCTS) algorithm to play a popular video game Hearthstone: Heroes of Warcraft.

Decision Making

Helping AI to Play Hearthstone: AAIA'17 Data Mining Challenge

no code implementations • 2 Aug 2017 • Andrzej Janusz, Maciej Świechowski, Tomasz Tajmajer

This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform.

Modular Multi-Objective Deep Reinforcement Learning with Decision Values

1 code implementation • 21 Apr 2017 • Tomasz Tajmajer

In this architecture we introduce decision values to improve the scalarization of multiple DQNs into a single action.

reinforcement-learning Reinforcement Learning (RL)