SAC postload optimizer for alpha

MushroomRL / mushroom-rl

Python library for Reinforcement Learning.

MIT License

814 stars 148 forks source link

SAC postload optimizer for alpha #139

Closed PuzeLiu closed 6 months ago

PuzeLiu commented 9 months ago

I've found out in SAC the optimizer for alpha is not loaded properly. The alpha parameter is not continued training after load the agent for the second time

boris-il-forte commented 9 months ago

Fixed in dev-v1.

The bugfix will be included in the 1.10.1 release

boris-il-forte commented 6 months ago

Fixed in 1.10.1