Pinned Repositories
EMTaskClustering
Implementation of EM-Task-Clustering from "Unsupervised Task Clustering for Multi-Task Reinforcement Learning"
Coding_Challenge
Deep reinforcement learning seminar coding challenge
DRL_Seminar_BlackJack
Deep Reinforcement Learning Seminar BlackJack Coding Challenge
map-reader
Tensorflow implementation of the map reading algorithm described in ‘Teaching a Machine to Read Maps with Deep Reinforcement Learning’
normalized-attention
Code publication to the paper "Normalized Attention Without Probability Cage"
SAVER
This repository contains the code to run the experiment (plus some additional experiments) described in the workshop paper “Quantile Regression Reinforcement Learning with State Aligned Vector Rewards” - https://openreview.net/forum?id=S1fuWRYCFm
TreeConnect
This repository contains a simple Keras implementation of the TreeConnect architecture presented in the corresponding paper "TreeConnect: A Sparse Alternative to Fully Connected Layers" published at the International Conference on Tools with Artificial Inteligence 2018. The code allows to reproduce the results presented on CIFAR10 using a CNN feature extractor (we refer to the paper for details).
OliverRichter's Repositories
OliverRichter/map-reader
Tensorflow implementation of the map reading algorithm described in ‘Teaching a Machine to Read Maps with Deep Reinforcement Learning’
OliverRichter/normalized-attention
Code publication to the paper "Normalized Attention Without Probability Cage"
OliverRichter/TreeConnect
This repository contains a simple Keras implementation of the TreeConnect architecture presented in the corresponding paper "TreeConnect: A Sparse Alternative to Fully Connected Layers" published at the International Conference on Tools with Artificial Inteligence 2018. The code allows to reproduce the results presented on CIFAR10 using a CNN feature extractor (we refer to the paper for details).
OliverRichter/SAVER
This repository contains the code to run the experiment (plus some additional experiments) described in the workshop paper “Quantile Regression Reinforcement Learning with State Aligned Vector Rewards” - https://openreview.net/forum?id=S1fuWRYCFm
OliverRichter/Coding_Challenge
Deep reinforcement learning seminar coding challenge
OliverRichter/DRL_Seminar_BlackJack
Deep Reinforcement Learning Seminar BlackJack Coding Challenge