Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition
This work addresses multi-agent coordination in a complex game environment, but it is incremental as it applies existing methods like reward shaping and curriculum learning to a new benchmark.
The authors tackled the challenge of the Pommerman Team Environment, a multi-agent benchmark with partial observability and sparse rewards, by developing a team of neural networks using deep reinforcement learning, which achieved 2nd place in the learning agents category of the inaugural competition.
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