Kyriakos Polymenakos's repositories
SafePILCO_Tool-Reproducibility
This repo reproduces experiments for SafePILCO for the tool paper submitted to QEST 2020
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Language:PythonMIT000
grokking
unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
Language:PythonMIT000
PILCO
PILCO in TensorFlow
Language:PythonMIT000
Language:C++GPL-2.0000
Safe-RL-Benchmark
A library to benchmark reinforcement learning algorithms