chiamp

muzero-cartpole

Applying DeepMind's MuZero algorithm to the cart pole environment in gym

fast-reinforcement-learning

Implementing DeepMind's Fast Reinforcement Learning paper, and adding additional features to generalize the algorithms

skill-expression-game-analysis

Finding a method to objectively quantify skill expression in games, using reinforcement learning

symbolic-regression-gradient-descent

Experimenting with symbolic regression via gradient descent using neural networks

sigmazero

Generalizing DeepMind's MuZero algorithm on stochastic environments

dqn-boardgames

A repo where I test the reinforcement learning algorithm DQN on board games

chiamp

My personal repository

flax

Flax is a neural network library for JAX that is designed for flexibility.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

orbax