Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition

April 20, 2019 · Entered Twilight · 🏛 arXiv.org

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, action_filter_random_player1.gif, action_prune.py, random_agent.py, simple_agent_cautious_bomb.py

Authors Chao Gao, Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor arXiv ID 1905.01360 Category cs.MA: Multiagent Systems Cross-listed cs.AI, cs.LG Citations 18 Venue arXiv.org Repository https://github.com/BorealisAI/pommerman-baseline ⭐ 37 Last Checked 2 months ago

Abstract

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 of 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 at: https://github.com/BorealisAI/pommerman-baseline