It’s never been more fun to be a reinforcement learning agent.
OpenAI
 @OpenAI
4 Mar 2019
We’re releasing a Neural MMO — a massively multiagent game environment that supports numerous populations of agents: blog.openai.com/neural-mmo/ - Code: github.com/openai/neural-mmo - 3D Client: github.com/jsuarez5341/neura…

Mar 4, 2019 · 5:25 PM UTC

2
25
3
191
Replying to @gdb
Super exciting. So many fun possibilities to alter the agent behavior, like: Guilds(agent controlled)/Factions(predetermined), reward for resource hoarding/ territory control, Hidden treasure, timed Loot Drops, symbol emotes allowing agent communication, Markets, world bosses