TLDRocket
Sign in

Environment Design

1 summarised story about Environment Design, each linking back to the original source. Browse all topics →

Monday, 4 March 2019

Neural MMO: A massively multiagent game environment

OpenAI Blog 7 years ago

OpenAI released Neural MMO, a game environment designed for training large numbers of reinforcement learning agents simultaneously. The platform supports a variable number of agents competing in a persistent world, with multiple species types present. The multi-agent setup encourages agents to explore different strategies and develop specialized behaviors rather than converging on single solutions.