PyTorch implementation of SAC (Soft Actor-Critic)

A simple and neat implementation of reinforcement learning algorithms.

Adversarial Patch defense using SegmentAndComplete (SAC) & Masked AutoEncoder (MAE)

Building and training a Furuta Pendulum Robot with an SAC/PPO reinforcement learning implementation

Discrete Soft Actor-Critic with Environment Parallelization, SEER, SAC+AE, SD-SAC and Munchausen Reinforcement Learning

Funções de Sistemas de Financiamento comparação Gráfica - SAC, PRICE, SAA - Matplotlib

Quadruped Ant-v4 Environment Training with Stable-Baselines3

Experimental version of Stable Baslines3 which expands SB3 2.2.1 to be able to define a multi algorithm training. Usage will be based on defer actions, observation space and rewards between its inner algorithms (PPO, DQN, SAC...). It is thought for projects which may rely on different strategies for different actions with a focused training

🛠️ Build and explore a minimal implementation of recursive language models with a REPL environment for OpenAI clients. Start hacking today!

A repository for easy understanding of codes in Deep Reinforcement Learning

Implementation of (Deep) Reinforcement Learning algorithms using PyTorch & TensorFlow2

Functions for Financial Mathematical calculations - Present Value, Future Value, Equivalent Rate, Financing Systems: SAC, PRICE, SAA.

A Reinforcement Learning Library [dev] DDPG,TD3,SAC,PPO and more

A novel approach to solve Contextual Reinforcement Learning

This repository contains a collection of Python scripts and programs related to seismology.

Reproduce results of continuous SAC and CrossQ in `mujoco` environments with PyTorch

a Python library that implements various reinforcement learning algorithms using PyTorch and Gymnasium

Modularized Implementation of Deep RL Algorithms in PyTorch

Simple yet efficient implementations of Model Free Reinforcement Learning algorithms in Pytorch

A simulation and training package for a directly controlled single-component rigid tool manipulating disks in a 2D environment. Uses PyBox2D for the simulation, pytorch for the training.