diff --git a/README.md b/README.md index b8329af23f514ff362e9b94373675bc8f98b2f67..f55a50514dcf701dbc46dc8678308489d5defd40 100644 --- a/README.md +++ b/README.md @@ -14,8 +14,8 @@ To set up a Python virtual environment, use the following commands: python -m venv venv source venv/bin/activate # On macOS/Linux venv\Scripts\activate # On Windows bash -Copy -Edit + + ### Required Libraries @@ -24,18 +24,29 @@ Install the necessary libraries with the following command: pip install gymnasium stable-baselines3 wandb panda-gym torch matplotlib csharp -Copy -Edit + + ## Project Structure The project is organized as follows: -. ├── README.md ├── a2c_sb3_cartpole.py ├── a2c_sb3_panda_reach.py ├── evaluate_reinforce_cartpole.py ├── reinforce_cartpole.py ├── reward_plot.png ├── script_hub.py ├── test.py ├── training_wandb.py ├── venv └── wandb +. +├── README.md +├── a2c_sb3_cartpole.py +├── a2c_sb3_panda_reach.py +├── evaluate_reinforce_cartpole.py +├── reinforce_cartpole.py +├── reward_plot.png +├── script_hub.py +├── test.py +├── training_wandb.py +├── venv +└── wandb + + + -markdown -Copy -Edit ## Experiment Tracking @@ -60,8 +71,8 @@ To run the CartPole experiment, use the following command: python a2c_sb3_cartpole.py bash -Copy -Edit + + ### Running the Panda Reach Experiment @@ -70,8 +81,8 @@ To run the Panda Reach experiment, use the following command: python a2c_sb3_panda_reach.py yaml -Copy -Edit + + ### Evaluating the CartPole Model @@ -80,8 +91,8 @@ To evaluate the CartPole model, use the following command: python evaluate_reinforce_cartpole.py shell -Copy -Edit + + ## Results