docs/README_legacy.md

Project Mahoraga

This is a controlled reinforcement learning environment designed to demonstrate adaptive intelligence via a resistance trade-off system.

Project Structure

• env/: Contains the core logic for the environment, state handling, enemy behavior, and mechanics.
• utils/: Contains constants and validators for actions.
• tests/: Contains manual basic sanity tests to verify correct environment behavior.
• main.py: Entry point to run a single manual episode with random actions.