I tried Reinforcement Learning for the first time!
I was always amazed by how giant robots can be trained through simulations using reinforcement learning.
I am grateful to try this for the first time in my life with the CartPole-v1 environment from OpenAI Gym.
In this project, I trained an agent to balance a pole on a moving cart by applying a fixed amount of force either to the left or right side.
- OpenAI Gym environment:
CartPole-v1 - Pygame for visualization
The agent learns to keep the pole balanced for as long as possible without falling.
- Improve training with better algorithms (e.g., DQN, Policy Gradients)
- Save and load trained models
- Compare results with different hyperparameters
Thanks to OpenAI Gym for providing such an amazing environment to learn reinforcement learning.