Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math

Source files for the course "Mathematics for Macroeconomics"

PyDiffGame is a Python implementation of a Nash Equilibrium solution to Differential Games, based on a reduction of Game Hamilton-Bellman-Jacobi (GHJB) equations to Game Algebraic and Differential Riccati equations, associated with Multi-Objective Dynamical Control Systems

Find the shortest route using A* algorithm and graphs (Route Planner application)

Infinite horizon policy optimization for drone navigation. Graded project for the ETH course "Dynamic Programming and Optimal Control".

Algorithms for Policy Evaluation, Estimation of Action Values, Policy Improvement, Policy Iteration, Truncated Policy Evaluation, Truncated Policy Iteration, Value Iteration . From Udacity's Deep Reinforcement Learning Nanodegree program.

A GPU-accelerated toolbox for hyperbolic PDEs in a weaker (viscosity) sense. It leverages the integral to the solution of the conservation of momentum problem (being equivalent to the derivative of Hamilton-Jacobi equations) in one spatial dimension. We resolve such hyperbolic differential equations using wave-front propagating schemes on a spat…

⚡️Adaptive Q-Network [ICLR 25] is one of the first approach to automatically tune RL agents hyperparameters by considering the specificities of reinforcement learning, i.e., non-stationarities⚡️

Foundations Of Intelligent Learning Agents (FILA) Assignments

✨iterated Q-Network [TMLR 25] learns several Bellman iterations in parallel instead of learning them sequentially✨

Reinforcement Learning applied to Autonomous Networking to issue scheduling and decision to drones.

Policy Iteration for Continuous Dynamics

Solving high dimensional HJB equation using tensor decomposition

🌸Eau De Q-Network [RLC 25] is a pruning algorithm specifically designed for RL which discovers the final sparsity level of the networks🌸

A visualization tool for policy iteration and value iteration

Dynamic Optimization project working on an economic model

Q-Learning from scratch in Python

🤖 Implementation of policy evaluation using dynamic programming to approximate a value function using an equiprobable random policy on Frozen Lake Grid World.

Reinforcement learning

CSCI-561 AI Assignments.