/DDPG_MARL_Simple_Tag

Reinforcement Learning using DDPG Algo on a Multi-agent Environment, name 'Simple_Tag'

Primary LanguagePython

Deep-Deterministic Policy Gradient Algorithm applied to the multi-agent environment tag consisting of 1 v 1 test match.

Dependencies: Pytorch Gym Multi-Agent Particle Environment (https://github.com/openai/multiagent-particle-envs)

Usage: Edit /multiagent/scenarios/simple_tag.py so that there is 1 Agent and 1 Adversary

python3 world_tag.py

This repo is part of the final project of the Move37 course from School of AI (https://www.theschool.ai)