Optimized-MC-Dropout-Using-DRL

Model MC-dropout in a Deep Reinforcement Learning (DRL) framework, to find the optimial passes needed for producing predefined confidence level.

policy-gradient-methods

policy gradient methods implementation using TensorFlow and Open AI Gym

papers

papers I read and influenced by

elisim.github.io

elisim

Linux-Shell

simple C implementation for a Linux shell

openai-evals-hebrew-word-gender-data

Data for OpenAI Evals - word gender of hebrew nouns.

deep-q-learning

Q-learning and Deep-Q-Learning from scratch using Open AI gym environments