Imptementation of some RL algorithms.

A clean PyTorch implementation of PPO, SAC, and TD3 made from scratch. It is built for testing and comparing continuous control RL algorithms on complex environments such as BipedalWalker-v3.

Cuda accelerated library for Rl training.

🐱 Create a living cat AI that exhibits emotions, reactions, and realistic behavior for an engaging and interactive experience.

reinforcement learning

This repository contains implementations of several deep RL algorithm : DQN, PPO and DDPG. They can be used for ATARI games.

A novel approach to solve Contextual Reinforcement Learning

Reinforcement learning for crawling robot

ML a simple track game

Deep reinforcement learning framework for fast prototyping based on PyTorch

Implementations of modern machine-learning papers , including PPO ,PPG and POP3D

Implemented Behavior Cloning, DAgger, Double Q-Learning, Dueling DQN, and Proximal Policy Optimization (PPO) in a simulated environment and analyzed/compared their performance in terms of efficiency, stability, and generalization.

AI DQN RL

Deep Reinforcement Learning Agent that learns to plays League of Legends

增加verl ascend适配；做一些小的改进

Project work for Autonomous and Adaptive Systems, UNIBO 2022

An implementation from the state-of-the-art family of reinforcement learning algorithms Proximal Policy Optimization using normalized Generalized Advantage Estimation and optional batch mode training. The loss function incorporates an entropy bonus.

This project designs a paradigm of dynamic partitioning system which uses reinforcement learning algorithm, PPO, to solve the dynamic workload problem in vertical partitioning field.

RL-Grid-Optimizer

Deep Reinforcement Learning for Multi-Robot Path Planning using PyTorch, Ray RLlib, and Gymnasium.