Skip to content

v0.1.13 MakeEvolvable, Curriculum Learning and Self-play 馃
Compare
Choose a tag to compare
@nicku-a nicku-a released this 27 Oct 13:21
· 722 commits to main since this release
v0.1.13
d81abb5
This commit was created on GitHub.com and signed with GitHub鈥檚 verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

AgileRL v0.1.13 introduces more flexibility, allowing users to define their own custom networks and use them with our algorithms and SOTA hyperparameter optimisation. Additionally, we have continued collaborating with the Farama Foundation to bring you another tutorial.

This release includes the following:

  • MakeEvolvable wrapper to make any sequential network evolvable - wrap any CNN or MLP to make them compatible with AgileRL algorithms and evolutionary hyperparameter optimisation! 馃Й
  • Use pre-trained networks with AgileRL - load any PyTorch nn.module network into AgileRL to automatically make it evolvable. 馃帗
  • Self-play tutorial that harnesses curriculum learning to train a DQN agent to play connect4! 馃弳

Stay tuned for more updates coming soon!

Assets 2