Name: Aubret Arthur
Type: User
Company: Frankfurt institute for Advanced Studies
Bio: Postdoc interested in self-supervised representation learning and developmental machine learning
Twitter: Arthur_Aubret
Location: Frankfurt-am-Main
Blog: https://aubret.github.io/
Aubret Arthur's Projects
Datasets for Data-driven Deep Reinforcement Learning with Atari (wrapper for datasets released by Google)
Deep Learning for Java, Scala & Clojure on Hadoop & Spark With GPUs - From Skymind
Implementation for ICML 2019 paper, EMI: Exploration with Mutual Information.
Topic Modelling for Humans
Official codes for the paper "In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation"
Minimalistic gridworld environment for OpenAI Gym
Codes to export blender models to tdw
code for "Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders".
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.