Skip to content

v0.5.2
Compare
Choose a tag to compare
@michele-milesi michele-milesi released this 12 Jan 08:39
· 66 commits to main since this release
v0.5.2
2c9c0b3
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

v0.5.2 Release Notes

  • Added A2C algorithm (#33).
  • Added a new how-to on how to add an external algorithm (no need to clone sheeprl locally) in (#175).
  • Added optimizations (#177):
    • Metrics are instantiated only when needed.
    • Removed the torch.cat() operation between empty and dense tensors in the MultiEncoder class.
    • Added possibility not to test the agent after training.
  • Fixed GitHub actions workflow (#180).
  • Fixed bugs (#181, #183).
  • Added benchmarks with respect to StableBaselines3 (#185).
  • Added BernoulliSafeMode distribution, which is a Bernoulli distribution where the mode is computed safely, i.e. it returns self.probs > 0.5 without seeting any NaN (#186) .
Assets 2
Loading