Simple EnergyPlus environments for control optimization using reinforcement learning

Code for my Master's thesis, game theory for adversarial autonomous vehicle platooning scenarios

Reinforcement learning based automated parking system (Gymnasium and Ray RLlib)

The Learning and Experiencing Cycle Interface (LExCI).

Gymnasium environments for classic Inventory Management problems (Newsvendor, Multi-Echelon, Network), adapted from OR-Gym. Provides RL environments and comprehensive benchmarking scripts comparing Heuristic, SB3, and RLlib agents.

Notebooks and exercises for the Fast Deep Reinforcement Learning Course https://courses.dibya.online/p/fastdeeprl

Ray RLlib cookie cutter.

Integration of Ray RLlib into CARLA Autonomous Driving Simulator 🚙

Multi-agent reinforcement learning framework for training NPCs in browser-based 3D voxel hide-and-seek using PPO and WebSocket communication between Ray RLlib and THREE.js

Source code of experiments with MARL and FaaS of Emanuele Petriglia.

Deep Reinforcement Learning trading agent based on Custom Transformer architecture and Ray RLlib. Features vectorized feature engineering and conservative backtesting environment.

🎮 Train NPCs using Proximal Policy Optimization in a browser-based 3D voxel environment for dynamic multi-agent reinforcement learning.