search

PathmindAI / nativerl

Train reinforcement learning agents using AnyLogic or Python-based simulations
Apache License 2.0
19 stars 4 forks source link

Add support for pathmind simulations and auto-norm #424

Closed slinlee closed 2 years ago

slinlee commented 2 years ago

@brettskymind since pathmind simulations have reward terms built in, it makes sense to enable auto balancing/auto-norm.

part of adding support for pathmind simulations in the webapp https://github.com/SkymindIO/pathmind-webapp/issues/2934 cc @ejunprung

thetwotravelers commented 2 years ago

@slinlee Btw, do you want me to build this support on the newest auto-balancing/auto-norm branch: bg_nb or create a new branch from current dev?

slinlee commented 2 years ago

@brettskymind how much do the changes overlap?

thetwotravelers commented 2 years ago

Already made the changes. They don’t really overlap, so I’ll go with Dev

slinlee commented 2 years ago

perfecto

thetwotravelers commented 2 years ago

enabled in this https://github.com/SkymindIO/nativerl/pull/437 with support by this https://github.com/PathmindAI/pathmind-api/pull/15

slinlee commented 2 years ago

We'll keep this open until the PR are merged