Pinned Repositories
adversarial_attacks
Implementation of classic adversarial attack and defense methods on basic classification problems
alphazero_singleplayer
Single player Alpha Zero implementation
bnp_re
docs
TensorFlow documentation
gnewsclient
An easy-to-use python client for Google News feeds.
HMM_PySpark
Implementation of the Viterbi algorithm (EM) for the estimation of parameters of Hidden Markov Model in a distributed fashion (using PySpark).
hydrogym
OpenAI Gym API-compliant challenge problems in data-driven modeling and control of fluid dynamics for reinforcement learning algorithms, evolutionary algorithms, classical control, and beyond.
iCEM
improved Cross Entropy Method for trajectory optimization
lbmpc_semimarkov
Repository for the article: "Increasing Information for Model Predictive Control with Semi-Markov Decision Processes"
singularity-hydrogym
Combine singularity containers with hydrogym and stable-baselines3
ReHoss's Repositories
ReHoss/adversarial_attacks
Implementation of classic adversarial attack and defense methods on basic classification problems
ReHoss/gnewsclient
An easy-to-use python client for Google News feeds.
ReHoss/HMM_PySpark
Implementation of the Viterbi algorithm (EM) for the estimation of parameters of Hidden Markov Model in a distributed fashion (using PySpark).
ReHoss/lbmpc_semimarkov
Repository for the article: "Increasing Information for Model Predictive Control with Semi-Markov Decision Processes"
ReHoss/singularity-hydrogym
Combine singularity containers with hydrogym and stable-baselines3
ReHoss/alphazero_singleplayer
Single player Alpha Zero implementation
ReHoss/bnp_re
ReHoss/docs
TensorFlow documentation
ReHoss/hydrogym
OpenAI Gym API-compliant challenge problems in data-driven modeling and control of fluid dynamics for reinforcement learning algorithms, evolutionary algorithms, classical control, and beyond.
ReHoss/iCEM
improved Cross Entropy Method for trajectory optimization
ReHoss/Monte_Carlo_methods
Application of some Monte Carlo methods (e.g. Recycling rejected values in accept-reject methods ) written in R
ReHoss/my_projects
Acadamic projects: mostly computational statistics, deep learning and numerical analysis.
ReHoss/ResNet_Go
Residual Network model to learn policy and value in computer Go using Facebook ELF data.
ReHoss/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
ReHoss/stable-baselines3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
ReHoss/streaming_anomaly_detector
Class project: flink anomaly detector
ReHoss/test_alphazero