A custom reinforcement learning environment for the Hot or Cold game. The agent navigates a 100x100 grid to find a randomly placed target while receiving rewards based on proximity and success.
python
machine-learning
reinforcement-learning
openai-gym
gym-environment
2d-environment
reinforcement-learning-environments
custom-gym-environment
hot-or-cold
-
Updated
Sep 20, 2024 - Jupyter Notebook