GitHub

Comparing a classical Destination Dispatching algorithm against a PPO-trained reinforcement learning agent in a custom-built Gymnasium simulation environment.

elevator-ai/ ├── environment/ │ ├── building.py # Core simulation entities │ ├── elevator_env.py # Gymnasium environment │ └── traffic_patterns.py # Probabilistic passenger spawning ├── agents/ │ ├── ...
IEEE

UAV path planning based on the improved PPO algorithm

Abstract: In this paper, we consider the problem of unmanned aerial vehicle (UAV) path planning. The traditional path planning algorithm has the problems of low efficiency and poor adaptability, so ...
GitHub

LLM-guided reinforcement learning for BipedalWalker-v3

Version 2 introduces physical controls, custom terrain handling, and a continuous training pipeline. llm_rl_bipedal/ ├── config.py # Central configuration for hyper-parameters, API keys, etc. ├── main ...
IEEE

Multi-Robot Collaboration for Dynamic Environments: A Study Based on the Improved PPO Algorithm

Abstract: With the expanding applications of multi-robot systems in complex dynamic environments, efficiently coordinating multiple robots to complete intricate tasks has become a hot research topic.