Pinned Loading

1. jaxrl jaxrl Public

   A actor critic implementation written with flax/nnx

   Python 1

2. sentiment_analysis sentiment_analysis Public

   A 109 million parameter generative language trained on Yelp data for next token prediction and review rating prediction.

   Jupyter Notebook 1

3. tictactoe-rl tictactoe-rl Public

   Teaching reinforcement learning agents to master tictactoe with self-play.

   Jupyter Notebook 1