Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition
arXiv:1905.01360
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
arXiv comment4th Multidisciplinary Conference on Reinforcement Learning and Decision Making
References in corpus (2)
Cited by in corpus (9)
- A Survey and Critique of Multiagent Deep Reinforcement Learning
- On Multi-Agent Learning in Team Sports Games
- Accelerating Training in Pommerman with Imitation and Reinforcement Learning
- Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop
- Learning to Play Imperfect-Information Games by Imitating an Oracle Planner
- Developing a Successful Bomberman Agent
- School of hard knocks: Curriculum analysis for Pommerman with a fixed computational budget
- Towards robust and domain agnostic reinforcement learning competitions
- Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman