Skip to Main content Skip to Navigation
Conference papers

Deep Reinforcement Learning in Strategic Board Game Environments

Abstract : In this paper we propose a novel Deep Reinforcement Learning (DRL) algorithm that uses the concept of “action-dependent state features”, and exploits it to approximate the Q-values locally, employing a deep neural network with parallel Long Short Term Memory (LSTM) components, each one responsible for computing an action-related Q-value. As such, all computations occur simultaneously, and there is no need to employ “target” networks and experience replay, which are techniques regularly used in the DRL literature. Moreover, our algorithm does not require previous training experiences, but trains itself online during game play. We tested our approach in the Settlers Of Catan multi-player strategic board game. Our results confirm the effectiveness of our approach, since it outperforms several competitors, including the state-of-the-art jSettler heuristic algorithm devised for this particular domain.
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02124411
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Thursday, May 9, 2019 - 3:16:42 PM
Last modification on : Sunday, June 14, 2020 - 3:29:01 AM
Long-term archiving on: : Tuesday, October 1, 2019 - 4:00:05 PM

File

xenou_22647.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02124411, version 1
  • OATAO : 22647

Citation

Konstantia Xenou, Georgios Chalkiadakis, Stergos Afantenos. Deep Reinforcement Learning in Strategic Board Game Environments. 16th European Conference on Multi-Agent Systems (EUMAS 2018), Dec 2018, Bergen, Norway. pp.233-248. ⟨hal-02124411⟩

Share

Metrics

Record views

85

Files downloads

1456