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.

A collection of reinforcement learning projects exploring different algorithms in various simulated environments.

Quadruped robot dog walking simulation and RL policy training

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.

Clean DQN-to-PPO reinforcement learning implementations in PyTorch

A novel approach to solve Contextual Reinforcement Learning

ML a simple track game

3D container loading optimization using classical RL (PPO, A3C) and quantum-classical hybrid RL (Quantum PPO, Quantum A3C) with VQE actor and QAOA critic circuit

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

Implementing ppo based on openai/baselines, but more readable.

PPO algoritması ve SUMO kullanarak akıllı trafik ışığı yönetimi projesi.

Implementation of policy based reinforcement learning algorithms

A prototype RAG system that explains CatBoost code in housing data use-cases.

Final Project for CSE592- Foundations of AI

Deep RL agent that solves LunarLander-v2 using PPO.

ROS 2 Jazzy + Gazebo Sim + PPO project for autonomous mobile robot navigation using reinforcement learning

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

Unofficial PyTorch reproduction of MSPM: A Modularized and Scalable Multi-Agent RL System for Portfolio Management (PLOS ONE, 2022)