Pytorch version of Dreamer, which follows the original TF v2 codes.
-
Updated
Feb 7, 2022 - Python
Pytorch version of Dreamer, which follows the original TF v2 codes.
Various reinforcement learning algorithms implemented on the frozen lake grid world.
PyTorch implementation of Combined Reinforcement Learning via Abstract Representations
Simple world models lead to good abstractions, Google Cerebra internship 2020/master thesis at EPFL LCN 2021 ⬛◼️▪️🔦
Master Thesis project
This is a Model-Based Reinforcement Learning implementation based on a modular software architecture suitable for extension and easy to understand and use.
This is the official PyTorch implementation of my Master thesis. The main goal of this work was to optimize latent dynamics models with unsupervised representation learning.
Select the most appropriate model out of a library of models by assessing the performance of the models online
Code for Tackling Long-Horizon Tasks with Model-based Offline Reinforcement Learning
Numerical Evidence for Sample Efficiency of Model-Based over Model-Free Reinforcement Learning Control of Partial Differential Equations [ECC'24]
Official implementation of L4DC 2023 paper Transition Occupancy Matching -Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching
The repo for the FERMI FEL paper using model-based and model-free reinforcement learning methods to solve a particle accelerator operation problem.
OpenAI Gym blackjack environment (v1)
Official codebase for "Privileged Sensing Scaffolds Reinforcement Learning", contains the Scaffolder algorithm and Sensory Scaffolding Suite.
Code for "Dream and Search to Control: Latent Space Planning for Continuous Control"
[AAAI 2022] The official implementation of "DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning"
Soft Actor-Critic implementation with SOTA model-free extension (REDQ) and SOTA model-based extension (MBPO).
Dreamer on JAX
Code for Asynchronous Methods for Model-Based Reinforcement Learning
Add a description, image, and links to the model-based-reinforcement-learning topic page so that developers can more easily learn about it.
To associate your repository with the model-based-reinforcement-learning topic, visit your repo's landing page and select "manage topics."