This is the code repository for my thesis
-
Updated
Jun 6, 2017 - Python
This is the code repository for my thesis
Customisable Unified Physical Simulations (CUPS) for Reinforcement Learning. Experiments run on the ai2thor environment (http://ai2thor.allenai.org/) e.g. using A3C, RainbowDQN and A3C_GA (Gated Attention multi-modal fusion) for Task-Oriented Language Grounding (tasks specified by natural language instructions) e.g. "Pick up the Cup or else"
Model-based Policy Gradients
CaDM: Context-aware Dynamics Model for Generalization in Model-based Reinforcement Learning
Model-based Reinforcement Learning Framework
A Model-based Agent, for chinese speech recognize.
Model-based tomographic reconstruction for different acquisition geometries
Model-based AI approach for network and service coordination leveraging uncertain traffic forecasts
Algorithmic Methods of Model-based Medical Image Segmentation Using Python
The goal of this repository is to provide a gym-compatible library to easily perform model-based Reinforcement Learning experiments using PyTorch. The library makes it easier to create learnable environments and ensembles of networks that can be used to learn the dynamics of an environment.
Project for the course "Foundations of Reinforcement Learning" 2021 at ETH Zurich
Skill-based Model-based Reinforcement Learning (CoRL 2022)
Simulating a futuristic package delivery service using drones.
Probabilistic modeling using PyStan with demonstrative case study experiments from Christopher Bishop's Model-based Machine Learning.
Code for FLEX, a fast, adaptive and flexible model-based reinforcement learning exploration algorithm.
Free-breathing myocardial T1 mapping with Physically-Constrained Motion Correction
code for paper 'Comparison of Model Free and Model-Based Learning-Informed Planning for PointGoal Navigation'
A PyTorch-powered differentiable image reconstruction/optimization toolbox
A Model-Based Signal Processing Library Working With Windowed Linear State-Space and Polynomial Signal Models.
TOmographic MOdel-BAsed Reconstruction (ToMoBAR) software
Add a description, image, and links to the model-based topic page so that developers can more easily learn about it.
To associate your repository with the model-based topic, visit your repo's landing page and select "manage topics."