🤖 TSwR_projekt

Comparison of Reinforcement Learning and Classical Control with Feedback Linearization

This project uses the Reacher (Mujoco) environment from the Gymnasium library.

• More about the MuJoCo Reacher environment
• RL algorithms we used

---

🎯 Project Goals

1. Reinforcement Learning (RL)
   Training an agent to reach the target as quickly as possible in the Reacher environment.

2. Classical Control
   Model identification and implementation of control using feedback linearization and trajectory planning.

3. Method Comparison
   Performance analysis of both approaches in terms of accuracy, stability, and speed of reaching the target.

---

🛠️ Installation and Running

Clone the repository

git clone https://github.com/SirErico/TSwR_projekt
cd TSwR_projekt

Create a virtual environment

python3 -m venv venv
source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Tensorboard

tensorboard --logdir .rl/[RL_ALGORITHM]/logs/