kyr-pol

Kyriakos Polymenakos's repositories

To share and review code (and maybe reports) regarding the research project titled 'Safe model-based policy search'

Language:Jupyter Notebook1 10

This repo reproduces experiments for SafePILCO for the tool paper submitted to QEST 2020

Language:Python100

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Language:PythonMIT000

Collaborative filtering with the GP-LVM

Language:MATLABBSD-3-Clause010

Gaussian processes in TensorFlow

Language:PythonApache-2.0010

unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"

Language:PythonMIT000

PILCO in TensorFlow

Language:PythonMIT000

Language:C++GPL-2.0000

A library to benchmark reinforcement learning algorithms

Language:PythonMIT010

Safe Bayesian Optimization

Language:PythonMIT010