神經MMO 2.0：大規模多任務增強版的大規模多智能體學習

摘要

Neural MMO 2.0 是一個用於強化學習研究的大規模多智能體環境。這個新版本的關鍵特點是一個靈活的任務系統，允許使用者定義廣泛的目標和獎勵信號。我們挑戰研究人員訓練能夠泛化到在訓練過程中從未見過的任務、地圖和對手的智能體。Neural MMO 具有128個智能體的程序生成地圖，在標準設置中，並支持多達。2.0 版本是其前身的完全重寫，性能提高了三倍，並與 CleanRL 兼容。我們將該平台作為免費和開源軟件發布，提供全面的文檔，可在 neuralmmo.github.io 獲得，並且有一個活躍的社區 Discord。為了激發對這個新平台的初步研究，我們同時在 NeurIPS 2023 舉辦一場競賽。

English

Neural MMO 2.0 is a massively multi-agent environment for reinforcement learning research. The key feature of this new version is a flexible task system that allows users to define a broad range of objectives and reward signals. We challenge researchers to train agents capable of generalizing to tasks, maps, and opponents never seen during training. Neural MMO features procedurally generated maps with 128 agents in the standard setting and support for up to. Version 2.0 is a complete rewrite of its predecessor with three-fold improved performance and compatibility with CleanRL. We release the platform as free and open-source software with comprehensive documentation available at neuralmmo.github.io and an active community Discord. To spark initial research on this new platform, we are concurrently running a competition at NeurIPS 2023.

神經MMO 2.0：大規模多任務增強版的大規模多智能體學習

Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning

摘要

Support