Pinned Loading

1. omega omega Public

   A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environments.

   Python 39 4

2. optax-adan optax-adan Public

   An implementation of adan optimizer for optax

   Python 7

3. dejax dejax Public

   Accelerated replay buffers in JAX

   Python 39 4

4. ml-notes ml-notes Public

   A collection of notes about various machine-learning related topics

   HTML

5. BlueSkies BlueSkies Public

   A simple canopy landing simulator

   JavaScript 13 5