vn0m

Only one LSTM per bot so there is no "master strategy" neural network. Interesting, if I'm not wrong, bots are learning independently.

vn0m

9 anni fadiscuss

I sense an opportunity to build an AI generating clothing lines. At least for the buzz.

vn0m

9 anni fadiscuss

This is truly amazing. GG Microsoft.

vn0m

9 anni fadiscuss

I'm not an expert but for me it's seems that the proposed approach doesn't compute the value function . By optimizing directly the policy function aren't we losing some key ingredient for generalization? I mean could this algorithm be used in a fully non deterministic environment ? Like human vs machine?

Submissions

Show HN: Division Swarm, the OS for Multi-Agent Systems

[untitled]

Hybrid Reward Architecture for Reinforcement Learning

comments