Implementation and visualization (some demos) of search and optimization algorithms.
-
Updated
Nov 30, 2021 - Python
Implementation and visualization (some demos) of search and optimization algorithms.
Model-based reinforcement learning using CEM, MPC and PETS
Cross Entropy Method (CEM) implemented under Pytorch, supporting batch dimension and receding horizon style optimization.
Efficient Model-Based Deep Reinforcement Learning with Predictive Control: Developed a Model-Based RL algorithm using MPC, achieving convergence in 200 episodes (best case) and 1000 episodes on average, outperforming SAC/DQN (10,000+ episodes). Enhanced sample efficiency by 80-90% using learned dynamics and CEM for trajectory optimization.
Reinforcement Learning Notebooks
Tools for using motion primitives like Dynamic Motion Primitives or Differentiable Linear Dynamic Systems in PyTorch.
Workshop code for the talk on Introduction to Reinforcement Learning: https://fosterelli.co/file/talk/introduction-to-reinforcement-learning.pdf
Automated tuning of hyperparameters using Cross Entropy Method for optimization (CEM).
Add a description, image, and links to the cross-entropy-method topic page so that developers can more easily learn about it.
To associate your repository with the cross-entropy-method topic, visit your repo's landing page and select "manage topics."