{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/190501360","title":"Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition","arxiv_id":"1905.01360","date":"2019-04-20","proceeding":null,"authors":["Chao Gao","Pablo Hernandez-Leal","Bilal Kartal","Matthew E. Taylor"],"abstract":"The Pommerman Team Environment is a recently proposed benchmark which\ninvolves a multi-agent domain with challenges such as partial observability,\ndecentralized execution (without communication), and very sparse and delayed\nrewards. The inaugural Pommerman Team Competition held at NeurIPS 2018 hosted\n25 participants who submitted a team of 2 agents. Our submission\nnn_team_skynet955_skynet955 won 2nd place of the \"learning agents'' category.\nOur team is composed of 2 neural networks trained with state of the art deep\nreinforcement learning algorithms and makes use of concepts like reward\nshaping, curriculum learning, and an automatic reasoning module for action\npruning. Here, we describe these elements and additionally we present a\ncollection of open-sourced agents that can be used for training and testing in\nthe Pommerman environment. Code available at:\nhttps://github.com/BorealisAI/pommerman-baseline","url_abs":"http://arxiv.org/abs/1905.01360v1","url_pdf":"http://arxiv.org/pdf/1905.01360v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"190501360","repo_url":"https://github.com/BorealisAI/pommerman-baseline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.01360","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}