no code implementations • 15 Apr 2024 • Linjie Xu, Zichuan Liu, Alexander Dockhorn, Diego Perez-Liebana, Jinyu Wang, Lei Song, Jiang Bian
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency.
1 code implementation • 5 Apr 2023 • Aditya Mohan, Carolin Benjamins, Konrad Wienecke, Alexander Dockhorn, Marius Lindauer
Addressing an important open question on the legitimacy of such dynamic AutoRL approaches, we provide thorough empirical evidence that the hyperparameter landscapes strongly vary over time across representative algorithms from RL literature (DQN, PPO, and SAC) in different kinds of environments (Cartpole, Bipedal Walker, and Hopper) This supports the theory that hyperparameters should be dynamically adjusted during training and shows the potential for more insights on AutoRL problems that can be gained through landscape analyses.
Hyperparameter Optimization Open-Ended Question Answering +1
1 code implementation • 30 May 2022 • Linjie Xu, Jorge Hurtado-Grueso, Dominic Jeurissen, Diego Perez Liebana, Alexander Dockhorn
In this paper, we propose Elastic MCTS, an algorithm that uses state abstraction to play strategy games.
1 code implementation • 21 Apr 2021 • Alexander Dockhorn, Jorge Hurtado-Grueso, Dominik Jeurissen, Linjie Xu, Diego Perez-Liebana
Portfolio methods represent a simple but efficient type of action abstraction which has shown to improve the performance of search-based agents in a range of strategy games.
no code implementations • 17 Apr 2021 • Diego Perez-Liebana, Cristina Guerrero-Romero, Alexander Dockhorn, Linjie Xu, Jorge Hurtado, Dominik Jeurissen
Designing agents that are able to achieve different play-styles while maintaining a competitive level of play is a difficult task, especially for games for which the research community has not found super-human performance yet, like strategy games.
1 code implementation • 25 Sep 2020 • Raluca D. Gaina, Martin Balla, Alexander Dockhorn, Raul Montoliu, Diego Perez-Liebana
This document describes the design and implementation of the Tabletop Games framework (TAG), a Java-based benchmark for developing modern board games for AI research.
no code implementations • 11 Sep 2020 • Diego Perez-Liebana, Alexander Dockhorn, Jorge Hurtado Grueso, Dominik Jeurissen
Stratega, a general strategy games framework, has been designed to foster research on computational intelligence for strategy games.
1 code implementation • 1 Sep 2019 • Alexander Dockhorn, Simon M. Lucas, Vanessa Volz, Ivan Bravi, Raluca D. Gaina, Diego Perez-Liebana
This paper examines learning approaches for forward models based on local cell transition functions.
no code implementations • 6 May 2019 • Alexander Dockhorn, Sanaz Mostaghim
The Hearthstone AI framework and competition motivates the development of artificial intelligence agents that can play collectible card games.
no code implementations • 29 Mar 2019 • Simon M. Lucas, Alexander Dockhorn, Vanessa Volz, Chris Bamford, Raluca D. Gaina, Ivan Bravi, Diego Perez-Liebana, Sanaz Mostaghim, Rudolf Kruse
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent.