joeryjoery

PhD Student in Reinforcement Learning at TU Delft.

TU DelftNetherlands

Pinned Repositories

brax
Massively parallel rigidbody physics simulation on accelerator hardware.
Language:Jupyter Notebook2.2k 35 342247
flax
Flax is a neural network library for JAX that is designed for flexibility.
Language:Python6k 86 898632
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Language:Python30k 328 5.5k2.7k
jaxopt
Hardware accelerated, batchable and differentiable optimizers in JAX.
Language:Python921 17 20764
acme
A library of reinforcement learning components and agents
Language:Python00
HierQ
Hierarchical multistep and Q(λ)
Language:Jupyter Notebook00
jit_env
An Agent-Environment interface with Jax transformation compatibility
Language:Python9 1 230
PyCartogram
Produce Cartograms in Python with Shapely, Geopandas and numpy.
Language:Python20
muzero
A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each other, and investigate reliability of learned MuZero MDP models.
Language:Jupyter Notebook154 8 724
wandb
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Language:Python8.9k 59 3.3k658

joeryjoery/jit_env
An Agent-Environment interface with Jax transformation compatibility
Language:Python9 1 230
joeryjoery/PyCartogram
Produce Cartograms in Python with Shapely, Geopandas and numpy.
Language:Python20
joeryjoery/acme
A library of reinforcement learning components and agents
Language:Python00
joeryjoery/HierQ
Hierarchical multistep and Q(λ)
Language:Jupyter Notebook00