The Pommerman Team Environment is a recently proposed benchmark which involves a multi-agent domain with challenges such as partial observability, decentralized execution (without communication), and very sparse and delayed rewards. The inaugural Pommerman Team Competition, held at NeurIPS 2018, hosted 25 participants who submitted a team of 2 agents. Our submission, nn_team_skynet955_skynet955, won 2nd place in the "learning agents'' category.

Our team is composed of 2 neural networks trained with state of the art deep reinforcement learning algorithms and makes use of concepts like reward shaping, curriculum learning, and an automatic reasoning module for action pruning. Here, we describe these elements and, additionally, we present a collection of open-sourced agents that can be used for training and testing in the Pommerman environment. Code available here.

BibTeX

@inproceedings{gao2019skynet,
  author = {Chao Gao and Pablo Hernandez-Leal and Bilal Kartal and Taylor, Matthew E.},
  title = {{Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition}},
  year = {2019},
  booktitle={4th Multidisciplinary Conference on Reinforcement Learning and Decision Making},
}