Crawling in Rogue's dungeons with (partitioned) A3C

@article{Asperti2018CrawlingIR,
  title={Crawling in Rogue's dungeons with (partitioned) A3C},
  author={A. Asperti and Daniele Cortesi and Francesco Sovrano},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.08685}
}
Rogue is a famous dungeon-crawling video-game of the 80ies, the ancestor of its gender. Rogue-like games are known for the necessity to explore partially observable and always different randomly-generated labyrinths, preventing any form of level replay. As such, they serve as a very natural and challenging task for reinforcement learning, requiring the acquisition of complex, non-reactive behaviors involving memory and planning. In this article we show how, exploiting a version of A3C… Expand
9 Citations
Crawling in Rogue's Dungeons With Deep Reinforcement Techniques
  • 2
Combining Experience Replay with Exploration by Random Network Distillation
  • Francesco Sovrano
  • Computer Science, Mathematics
  • 2019 IEEE Conference on Games (CoG)
  • 2019
  • 3
  • PDF
DeepCrawl: Deep Reinforcement Learning for Turn-based Strategy Games
  • 4
  • PDF
Deep Reinforcement Learning in Strategic Multi-Agent Games: the case of No-Press Diplomacy
  • PDF
Learning to grow: control of materials self-assembly using evolutionary reinforcement learning
  • 9
  • PDF
Subspace clustering for situation assessment in aquatic drones
  • 8
  • PDF

References

SHOWING 1-10 OF 20 REFERENCES
A Modular Deep-learning Environment for Rogue
  • 2
  • PDF
Rogue-Like Games as a Playground for Artificial Intelligence - Evolutionary Approach
  • 7
  • PDF
Rogueinabox: an Environment for Roguelike Learning
  • 4
  • PDF
FeUdal Networks for Hierarchical Reinforcement Learning
  • 425
  • PDF
ViZDoom: A Doom-based AI research platform for visual reinforcement learning
  • 455
  • PDF
Reinforcement Learning with Unsupervised Auxiliary Tasks
  • 724
  • Highly Influential
  • PDF
Multi-agent reinforcement learning: weighting and partitioning
  • 74
  • PDF
Deep Reinforcement Learning with Double Q-Learning
  • 2,548
  • PDF
Asynchronous Methods for Deep Reinforcement Learning
  • 4,004
  • Highly Influential
  • PDF
...
1
2
...