Ecosyste.ms: Repos

An open API service providing repository metadata for many open source software ecosystems.

GitHub / chauncygu / Safe-Reinforcement-Learning-Baselines

The repository is for safe reinforcement learning baselines.

JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chauncygu%2FSafe-Reinforcement-Learning-Baselines

Stars: 403
Forks: 70
Open Issues: 0

License: None
Language: Jupyter Notebook
Repo Size: 70.7 MB
Dependencies: 77

Created: over 2 years ago
Updated: about 1 month ago
Last pushed: about 1 month ago
Last synced: about 1 month ago

Topics: baseline, reinforcement-learning, safe

Files

Loading...

Readme

Loading...

Dependencies

Safe-RL/RL-Safety-Algorithms/setup.py pypi

Safe-RL/Safe-MBPO/requirements.txt pypi

gym ==0.17.2
h5py *
matplotlib *
mujoco-py ==2.0.2.13
numpy *
opencv-python *
torch ==1.4.0
tqdm *

Safe-RL/Safe-RL-Benchmark/requirements.txt pypi

futures >=3.0.5
numpy >=1.7
scipy >=0.19.0
six >=1.10

Safe-RL/Safe-RL-Benchmark/requirements_dev.txt pypi

GPy >=1.6.1 development
coverage >=4.3.4 development
flake8 >=3.3.0 development
gym >=0.8.0 development
mock >=2.0.0 development
nose >=1.3.7 development
nose-exclude >=0.5.0 development
pep8 >=1.7.0 development
pep8-naming >=0.4.1 development
pydocstyle >=1.1.1 development
sphinx >=1.5.3 development
tensorflow >=1.0.0 development
unittest2 >=1.1.0 development

Safe-RL/Safe-RL-Benchmark/setup.py pypi

futures *
numpy *
scipy *
six *

Safe-RL/safe-mbrl/baseline/setup.py pypi

gym *
joblib ==0.14.0
matplotlib ==3.1.1
mpi4py ==3.0.2
mujoco_py ==2.0.2.7
numpy *
seaborn ==0.8.1
tensorflow ==1.15.4

Safe-RL/safe-mbrl/env/setup.py pypi

gym *
joblib *
mujoco_py ==2.0.2.7
numpy *
xmltodict *

Safe-RL/AlwaysSafe/Pipfile pypi

Safe-RL/safe-mbrl/requirements.txt pypi

PyYAML ==5.4
joblib ==0.14.1
matplotlib ==3.1.3
mpi4py ==3.0.3
psutil ==5.7.2
seaborn ==0.8.1
tqdm ==4.48.0

Safe-RL/safe_learning/docs/requirements.txt pypi

mock *
numpydoc >=0.6
sphinx *
sphinx_rtd_theme >=0.1.8

Safe-RL/safe_learning/requirements.txt pypi

cvxpy >=1,<=1.0.15
future <=0.18.0
gpflow ==0.4.0
matplotlib <=4.0.0
numpy >=1.0,<1.15
scipy >=1.0.0<=1.2.1
scs ==2.0.2
tensorflow >=1.6.0,<=1.12.0

Safe-RL/safe_learning/requirements_dev.txt pypi

flake8 >=3.0,<=3.5.0 development
mock * development
pydocstyle >=2.0,<2.1 development
pytest ==4.6.9 development
pytest-cov ==2.8.1 development

Safe-RL/safe_learning/setup.py pypi

Safe-RL/safety-starter-agents/setup.py pypi

gym *
joblib ==0.14.0
matplotlib ==3.1.1
mpi4py ==3.0.2
mujoco_py ==2.0.2.7
numpy *
seaborn ==0.8.1
tensorflow ==1.13.1