Pommerman: A Multi-Agent Playground

By Cinjon Resnick, W. Eldridge, David R Ha, Denny Britz, Jakob N. Foerster, Julian Togelius, Kyunghyun Cho, Joan Bruna. 2018

90 citations recorded by the source corpus.

We present Pommerman, a multi-agent environment based on the classic console game Bomberman. Pommerman consists of a set of scenarios, each having at least four players and containing both cooperative and competitive aspects. We believe that success in Pommerman will require a diverse set of tools and methods, including planning, opponent/teammate modeling, game theory, and communication, and consequently can serve well as a multi-agent benchmark. To date, we have already hosted one competition, and our next one will be featured in the NIPS 2018 competition track.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

The StarCraft Multi-Agent Challenge (2019, background): “Resnick et al. (2018) propose a multi-agent environment based on the game Bomberman , encompassing a series of cooperative and adversarial tasks meant to provide a more challenging set of tasks with a relatively straightforward 2D state observation and simple grid-world-like action spaces.”
A survey and critique of multiagent deep reinforcement learning (2018, background): “hem [69, 71, 72]. 4.3. Open questions Finally, here we present some open questions for MDRL. On the challenge of sparse and delayed rewards. Recent MAL competitions and environments (e.g., Pommerman [112], Capture the ag [86], MARLO [113], Starcraft II [114], and Dota 2 [16]) have complex scenarios ”
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration (2020, background): “There has been a large body of platforms for various multi-agent tasks (Jaderberg et al., 2019; Samvelyan et al., 2019; OpenAI, 2018; Lowe et al., 2017; Resnick et al., 2018; Shu & Tian, 2018; Carroll et al., 2019; Suarez et al., 2019; Baker et al., 2019; Bard et al., 2020).”
Backplay: "Man muss immer umkehren" (2018, unknown): “Pommerman is a stochastic environment (Resnick et al., 2018) based on the classic console game Bomberman and will be a competition at NeurIPS 2018.”
Learning Transferable Cooperative Behavior in Multi-Agent Teams (2019, background): “Other ways of forming a ﬁxed size representation is to multi-channel grids or feature maps (Resnick et al., 2018), however, that unnecessarily increases the observation space of the agent and hence the complexity of the problem.”
Building Cooperative Embodied Agents Modularly with Large Language Models (2023, background): “…Samvelyan et al., 2019; Carroll et al., 2019; Puig et al., 2021; 2023), or use uninterpretable continuous vectors (Jiang & Lu, 2018; Das et al., 2019) or limited discrete symbols (Lowe et al., 2017; Jaques et al., 2019; Jain et al., 2020; Patel et al., 2021; Resnick et al., 2018) for communication.”
Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning (2019, methodology): “Other recently introduced game-based AI benchmarks, such as the OpenAI Retro Challenge (Nichol et al. 2018), Coin-Run (Cobbe et al. 2018), and Pommerman (Resnick et al. 2018) all feature various kinds of environment randomization.”
Competitive Experience Replay (2019, background): “Resnick et al. (2018b) and Salimans & Chen (2018) propose to train policies on Pommerman (Resnick et al., 2018a) and the Atari game ‘Montezumas Revenge’ by starting each episode from a different point along a demonstration.”