AI lab@Vrije Universiteit Brussel

AI lab@Vrije Universiteit Brussel's repositories

Sample-Efficient Reinforcement Learning with Bootstrapped Dual Policy Iteration

Language:PythonGPL-3.025 4 3

Language:Python7 70

Distributed Reinforcement Learning over HTTP

Language:PythonNOASSERTION5 40

Options with Option-Observation Initiation Sets, using Policy Gradient, Keras and the OpenAI Gym

Language:PythonGPL-3.03 50

Q-Value Weighted Regression for Reinforcement Learning with discrete or continuous actions

Language:PythonMIT100

Language:Scala1 40

Q-learning demo in a VR grid world

Language:C#GPL-3.0100

Theano-based implementation of Deep Q-learning

Language:Python040

Language:C++NOASSERTION040

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Language:PythonMIT000

Code for the Multi-Agent Learning Seminar Course

Language:Jupyter NotebookMIT050

Language:Jupyter Notebook050