Skip to content

BunnyLuwang/Aquatic-Waste-Perception-MultiAgentReinforcementLearning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Cooperative Multi-Agent Reinforcement Learning for Aquatic Waste Interception

This project studies decision-making under uncertainty in aquatic environments using single-agent and cooperative multi-agent reinforcement learning (MARL).

The environment simulates stochastic waste generation, flow-driven transport, and interception by mobile agents. The goal is to maximize total intercepted waste over an episode.


Key Features

  • Custom aquatic environment with stochastic dynamics
  • Random and greedy heuristic baselines
  • Single-agent PPO (Stable-Baselines3)
  • Cooperative multi-agent PPO (centralized training, joint actions)
  • Quantitative comparison of policies

Environment

  • Grid-based aquatic system
  • Upstream waste spawning
  • Downstream flow and drift
  • Local interception radius

Each episode represents an independent stochastic simulation.


Results

Policy Comparison

Mean episodic reward (± std):

  • Random (single-agent): ~12.7
  • PPO (single-agent): ~19.6
  • PPO (2-agent cooperative): ~27.4
  • Greedy heuristic: ~30.1

Cooperative MARL significantly improves performance over single-agent learning, approaching a strong heuristic baseline.


How to Run

Install dependencies

pip install -r requirements.txt

About

Cooperative Multi-Agent Reinforcement Learning for Aquatic waste interception #ResearchProject

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages