Skip to content

v1.2.3

Compare
Choose a tag to compare
@afrozenator afrozenator released this 25 Feb 17:00

Reformer

  • Reversible Transformer model for machine translation and other encoder-decoder tasks
  • Add code for beam search, sampling, and greedy decoding (see trax.models.beam_search.Search)
  • Memory-efficient attention classes have been re-written to use even less memory and to support faster decoding (see the new SelfAttention, LSHSelfAttention and EncDecAttention classes)

RL

  • Implemented the Advantage-Weighted Regression algorithm, a simple off-policy reinforcement learning algorithm.
  • Extracted out a PolicyBasedTrainer, so ppo_trainer.PPO and awr_trainer.AwrTrainer now both inherit from it.
  • Refactoring of the serialization code in the RL part, thanks to @koz4k !

Framework

  • A lot of code cleanup and refactoring of the core abstractions by Jonni, thanks Jonni!

TF Numpy