multi-agent-reinforcement-learning

code for published paper titled "Optimal CO2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: a Markov game perspective  "

Code for the paper "Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning", Advances in Neural Information Processing Systems (NeurIPS) 2024

Cooperative Multi-Agent RL environment. Tested with IPPO and MADDPG

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Integrated supply chain intelligence platform for disruption detection, demand forecasting, resource allocation, and route optimization using GNNs, TFT, MARL, and POMO.

Decentralized traffic signal control under camera-limited observability (IEEE Access submission)

Implicit Ensemble Training for efficient and robust multiagent reinforcement learning — connect-four training setup and configs.

Multi-agent RL traffic coordination for a driverless San Francisco — zero traffic lights, safety as a constraint, live 3D demo

Public arXiv-ready repository for county-scale farmland consolidation: centralized DRL versus township-decomposed MARL.

Research code supporting my doctoral dissertation on reinforcement learning, dynamic optimization, autonomous vehicles, and algorithmic pricing.

PettingZoo ConnectFour and TicTacToe examples, configured with Rye as dependency manager

Adaptive Learning of Centralized and Decentralized Rewards in Multi-agent Imitation Learning

Code accompanying the paper "Assessing the Optimality of Decentralized Inspection and Maintenance Policies for Stochastically Degrading Engineering Systems" by Prateek Bhustali and Charalampos Andriotis.

Emergent communication in multi-agent RL

Multi-agent system solving Sudoku riddle

3D gym environments to train RL agents to play the Slime Volleyball game in 3 dimensions using Webots as simulator.

Smart Pricing for NANCY using Multi-Agent Reinforcement Learning and Reverse Auction Theory. Smart_Pricing_MARL_NANCY is an open-source, EU-co-funded Smart Pricing Module (SPM) developed for the NANCY project. It leverages Multi-Agent Reinforcement Learning (MARL) and Reverse Auction Theory to calculate optimal pricing strategies.

Blueprint open source per un villaggio AI–umano: co-creazione, workflow multi-agente, metriche cognitive e strumenti peeragogici per il futuro dell’apprendimento.

An AI-powered, multi-agent pipeline that automatically discovers, scrapes, geocodes, validates, and persists comprehensive school data into a Supabase database — orchestrated entirely by CrewAI agents connected to your database via a live MCP server.