PyPI page
Home page
Author:
sup3rus3r
Summary:
Autonomous training loop for any sequential learning model — PPO, DQN, SAC, TD3, Rainbow DQN, Recurrent PPO for TensorFlow, PyTorch, and JAX/Flax; distributed async actor-learner (IMPALA + V-trace)
Latest version:
1.16.0
Required dependencies:
gymnasium
|
matplotlib
|
numpy
|
nvidia-cuda-nvcc-cu12
|
optuna
|
pyyaml
|
swig
|
tensorflow
Optional dependencies:
ale-py
|
black
|
flax
|
gymnasium
|
jax
|
mypy
|
onnx
|
onnxruntime
|
onnxscript
|
optax
|
pytest
|
pytest-cov
|
ruff
|
tensorboard
|
tensorflow
|
torch
|
torchaudio
|
torchvision
|
twine
|
wandb
Downloads last day:
342
Downloads last week:
1,246
Downloads last month:
2,996