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.

CE-ABC is a code to simulate the epidemic outbreaks with mechanistic models through a cross-entropy approximate Bayesian framework.

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.

Solving Tetris using Cross-Entropy Method

Reinforcement Learning Notebooks

Simulation experiments for optimizing objective function with Differential Evolution, Evolution Strategies and Cross Entropy Method (2 versions)

Simple implementation and comparison of three reinforcement learning models.

Model-Based RL Multi-Tasking with ReLAx

CEopt is a Matlab routine for non-convex optimization using the Cross-Entropy method and augmented Lagrangian formulation.

Train a Cross-Entropy Method in Policy-Based Methods with OpenAI Gtm's MountainCarContinous environment

Two dimensional optimisation algorithm using the Cross Entropy Method. Data is iteratively fitted to a Beta Distribution in the algorithm.

Tools for using motion primitives like Dynamic Motion Primitives or Differentiable Linear Dynamic Systems in PyTorch.

SpringpotTune is a Matlab package designed for fitting variable-order springpot models using the Cross-Entropy method.

CROSS-OPT is a Matlab package for optimizing truss structures with the Cross-Entropy method and augmented Lagrangian formulation.

FraCTune is a Matlab package for tuning fractional-order controllers with the Cross-Entropy method and augmented Lagrangian formulation.

Open AI Cartpole environment gradient ascent

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).