Deep RL framework for exploring state spaces of finite state machines.
-
Updated
Mar 4, 2022 - Jupyter Notebook
Deep RL framework for exploring state spaces of finite state machines.
PyBullet environments to use Reinforcement learning with Stable Baselines 3
A Guide to Problems and Solutions on Genetic Algorithms
The aim of this repository is the analysis and study of computer intelligence and in-depth learning techniques in the development of intelligent gaming agents.
This project implements an agent for playing the SonicTheHedgehog2 game from a ROM file using the Proximal Policy Optimization (PPO) algorithm from the stablebaselines3 library. The agent is trained to learn the optimal actions to take at each step in the game in order to complete the level and maximize the score.
Distributed training for RL algo on pytorch
Source code for the numerical experiments presented in the paper "On the Unreasonable Efficiency of State Space Clustering in Personalization Tasks".
Using Neural Network and Genetic Algorithm to play SnakeGame
Unified framework enabling machine learning-based training, simulation, and deployment of legged robots, compatible with various robot models and reinforcement learning algorithms, with PyBullet simulation and ROS integration.
Autonomous 1:10 race car with a reinforcement learning based approach
Implementation of RL algorithms using the stable baselines library
A custom OpenAI gym environment for training Tic-Tac-Toe agents with Stable-Baselines3
Pilotage d'un pendule de Furuta avec un Raspberry PI
Analyzing policy entropy of reinforcement learning agents
Implementation of T-REX and D-REX Inverse Reinforcement Learning (IRL) algorithm for learning form suboptimal demonstrations
In this project I pass through the principles and concepts of Reinforced Learning and I trained an agent to manage the energy resources
A bot largely inspired by Necto and trained using novel rewards functions
Train quadruped locomotion using reinforcement learning in Mujoco
In this project, I created an agent to solve the CartPole task using the stablebaselines3 library. CartPole is a problem from the OpenAI Gym catalog, in which the goal is to maintain balance of a wooden pole using motors attached to its ends. The agent must decide whether to move the pole left or right to maintain balance.
Add a description, image, and links to the stable-baselines3 topic page so that developers can more easily learn about it.
To associate your repository with the stable-baselines3 topic, visit your repo's landing page and select "manage topics."