Update app.py

app.py

@@ -1,42 +1,64 @@
-import gradio as gr
+from huggingface_hub import hf_hub_download, Repository
+import gym
 import numpy as np
 import os
 
-# Update the file name to the correct one
-q_table_path = 'q_table_frozenlake.npy'
-
-# Ensure the Q-table file exists in the expected path
-if not os.path.exists(q_table_path):
-    raise FileNotFoundError(f"Q-table file '{q_table_path}' not found. Please upload it to the correct directory.")
-
-# Load the Q-table
-q_table = np.load(q_table_path)
-
-# Define a function to make predictions based on the Q-table
-def predict_action(state):
-    try:
-        # Convert the input state into a format compatible with the Q-table
-        state = list(map(int, state.split(',')))  # Example: '0,1,2' => [0, 1, 2]
-        
-        # Ensure state indices are within the bounds of the Q-table
-        if any(s < 0 or s >= q_table.shape[0] for s in state):
-            return "Error: State values are out of range for the Q-table."
-
-        # Predict the action based on the state
-        action = np.argmax(q_table[state[0]])  # Assuming the first value in state is the row index
-        action_mapping = {0: "Move Left", 1: "Move Down", 2: "Move Right", 3: "Move Up"}
-        return f"The predicted action is: {action_mapping.get(action, 'Invalid Action')}"
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-# Create the Gradio interface with a more playful UI
-iface = gr.Interface(
-    fn=predict_action,
-    inputs=gr.Textbox(label="Enter State (comma-separated values)"),  # You could also add a dropdown or grid for a more playful input
-    outputs=gr.Textbox(label="Predicted Action"),
-    live=True,
-    theme="huggingface",  # Choose a theme that matches the playful environment
-)
-
-# Launch the interface
-iface.launch()
+# Define your username and repo name
+username = "willco-afk"  # Your Hugging Face username
+repo_name = "frozenslippery"  # Your Hugging Face Space name
+
+# Initialize your environment
+env = gym.make("FrozenLake-v1", is_slippery=True)  # Adjust based on your specific environment
+
+# Correct file path where the Q-table is located
+repo_id = "willco-afk/frozenslippery"
+file_path = "q_table_frozenlake.npy"  # Path to the Q-table file in the repo
+
+# Try downloading the Q-table
+try:
+    download_path = hf_hub_download(repo_id=repo_id, filename=file_path)
+    # Load the Q-table
+    q_table = np.load(download_path)
+except Exception as e:
+    print(f"Error downloading the Q-table: {e}")
+    # Handle the error (for example, by uploading the Q-table manually if needed)
+
+# Save the model (Q-table) as a .npz file in the repo's folder
+model_filename = "q_table_frozenlake.npz"
+np.save(model_filename, q_table)
+
+# Initialize the Hugging Face repo for the Space (no need to create it again)
+repo = Repository(local_dir=repo_name, clone_from=f"{username}/{repo_name}")
+
+# Add and push the model file to Hugging Face Hub
+repo.git_add(model_filename)  # Add the Q-table to the repo
+repo.git_commit("Add trained Q-table")  # Commit the Q-table
+repo.git_push()  # Push the changes to Hugging Face Hub
+
+# Write the README file with details
+readme_content = "# FrozenLake RL Model\n\n"
+readme_content += "This model represents a Q-learning agent for the `FrozenLake-v1` environment with `is_slippery=True`.\n\n"
+readme_content += "### Usage Instructions\n\n"
+readme_content += "To use this model, you need to initialize the FrozenLake environment using OpenAI's gym:\n\n"
+readme_content += "```python\n"
+readme_content += "import gym\n"
+readme_content += "env = gym.make('FrozenLake-v1', is_slippery=True)\n"
+readme_content += "```\n\n"
+readme_content += "### Model Details\n\n"
+readme_content += "This model uses a Q-table learned through Q-learning in the `FrozenLake-v1` environment. The agent was trained using the following parameters:\n\n"
+readme_content += "- **Learning Rate:** 0.1\n"
+readme_content += "- **Discount Factor (gamma):** 0.99\n"
+readme_content += "- **Exploration Rate (epsilon):** Decays from 1.0 to 0.01\n"
+readme_content += "- **Training Episodes:** 1000\n"
+readme_content += "- **Max Steps per Episode:** 100\n\n"
+readme_content += "### About the Environment\n\n"
+readme_content += "The `FrozenLake-v1` environment is a gridworld where the agent must navigate a frozen lake while avoiding holes. It can slip based on the `is_slippery` parameter, making the environment stochastic.\n"
+
+# Write the README file
+with open(f"{repo_name}/README.md", "w") as readme_file:
+    readme_file.write(readme_content)
+
+# Add and push the README file
+repo.git_add("README.md")
+repo.git_commit("Add README for FrozenLake RL model")
+repo.git_push()