ThomasLecat
Interested in reinforcement learning and deep learning. Research Engineer @InstaDeep
InstaDeepLondon
Pinned Repositories
ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
biostatistics
biostatistics
gym-bandit-environments
Multi-armed bandits environments for OpenAI Gym
learning-to-learn-1
Reproduction of the experiments 3.1.1 and 3.1.2 of the paper "Learning to Reinforcement Learn"
learning-to-learn-2
Reproduction of the experiment 3.1.2 on meta-learning described in the paper "Learning to Reinforcement Learn"
medicaldetectiontoolkit
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
ray
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
udacity-continuous-control
udacity-multiagent-tennis
udacity-navigation-project
ThomasLecat's Repositories
ThomasLecat/gym-bandit-environments
Multi-armed bandits environments for OpenAI Gym
ThomasLecat/learning-to-learn-2
Reproduction of the experiment 3.1.2 on meta-learning described in the paper "Learning to Reinforcement Learn"
ThomasLecat/biostatistics
biostatistics
ThomasLecat/learning-to-learn-1
Reproduction of the experiments 3.1.1 and 3.1.2 of the paper "Learning to Reinforcement Learn"
ThomasLecat/medicaldetectiontoolkit
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
ThomasLecat/ray
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
ThomasLecat/udacity-continuous-control
ThomasLecat/udacity-multiagent-tennis
ThomasLecat/udacity-navigation-project