Easily implement parallel training and distributed training. Machine learning library. Note.neuralnetwork.tf package include Llama2, Llama3, Gemma, CLIP, ViT, ConvNeXt, BEiT, Swin Transformer, Segformer, etc, these models built with Note are compatible with TensorFlow and can be trained with TensorFlow.

This study explores using RL for CSTR control, assessing effectiveness vs. traditional controllers (PID, MPC). RL learns optimal behavior to maximize rewards, outperforming NMPC with exploration and lower computational load.

OpenDILab Decision AI Engine

An elegant PyTorch deep reinforcement learning library.

Rosnav planner, based on DRL and designed to work with ROS and the whole arena-rosnav infrastructure.

Not interactive deep reinforcement learning book with no-framework code, copied math, no discussions. Adopted at only -1 university(Shanhe University, SHU). BTW, I like this virtual university, which english abbreviation happens to be the pinyin of one part of my Chinese name(Cai "Shu"qi).

A benchmark library for DRL-based flow control

Repository that houses the program used to investigate the control of subsystems in homes based on a DRL model. The program uses the EnergyPlus Python API and Ray's Tune and RLlib libraries.

深度学习脚手架

Simulation code and mathematic details of our paper in IEEE Communications Magazine: ''When the User-Centric Network Meets Mobile Edge Computing: Challenges and Optimization''

Using deep reinforcement learning to play Snake game. The used algorithm is PPO for discrete! It has the brilliant performance in the field of discrete action space just like in continuous action space. You just need half an hour to train the snake and then it can be as smart as you.|使用深度强化学习玩蛇游戏。 使用的算法是离散的 PPO！ 它在离散动作空间领域有着与连续动作空间一样的出色表现。

model-based deep reinforcement learning for flow control applications in CFD

Deep Reinforcement Learning approach to Environment-depented Aerodynamic Drone Design Optimization Problem

This repo implements the REINFORCE algorithm for solving the Cart Pole V1 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1.

This repo implements Deep Q-Network (DQN) for solving the Frozenlake-v1 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 in both 4x4 and 8x8 map sizes.

This repo implements Deep Q-Network (DQN) for solving the Cliff Walking v0 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 with the finest tuning.

This repo implements Deep Q-Network (DQN) for solving the Mountain Car v0 environment (discrete version) of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 with a custom reward function for faster convergence.

Interactive environment for training and testing a Deep Reinforcement Learning agent.

Attempt to reimplement the VTC2023-Spring 'Deep Reinforcement Learning-Based Resource Allocation for Cellular V2X Communications' paper