Duplicate from ThomasSimonini/Compare-Reinforcement-Learning-Agents

Co-authored-by: Thomas Simonini <ThomasSimonini@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/Compare-Reinforcement-Learning-Agents.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Compare-Reinforcement-Learning-Agents.iml" filepath="$PROJECT_DIR$/.idea/Compare-Reinforcement-Learning-Agents.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

README.md

@@ -0,0 +1,13 @@
+---
+title: Compare Reinforcement Learning Agents
+emoji: 👀
+colorFrom: blue
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.1.1
+app_file: app.py
+pinned: false
+duplicated_from: ThomasSimonini/Compare-Reinforcement-Learning-Agents
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+import requests.exceptions
+from huggingface_hub import HfApi, hf_hub_download
+from huggingface_hub.repocard import metadata_load
+
+app = gr.Blocks()
+
+def load_agent(model_id_1, model_id_2):
+    """
+    This function load the agent's video and results
+    :return: video_path
+    """
+    # Load the metrics
+    metadata_1 = get_metadata(model_id_1)
+    
+    # Get the accuracy
+    results_1 = parse_metrics_accuracy(metadata_1)
+    
+    # Load the video
+    video_path_1 = hf_hub_download(model_id_1, filename="replay.mp4")
+    
+    # Load the metrics
+    metadata_2 = get_metadata(model_id_2)
+    
+    # Get the accuracy
+    results_2 = parse_metrics_accuracy(metadata_2)
+    
+    # Load the video
+    video_path_2 = hf_hub_download(model_id_2, filename="replay.mp4")
+    
+    return model_id_1, video_path_1, results_1, model_id_2, video_path_2, results_2
+
+def parse_metrics_accuracy(meta):
+    if "model-index" not in meta:
+        return None
+    result = meta["model-index"][0]["results"]
+    metrics = result[0]["metrics"]
+    accuracy = metrics[0]["value"]
+    return accuracy
+
+def get_metadata(model_id):
+    """
+    Get the metadata of the model repo
+    :param model_id:
+    :return: metadata
+    """
+    try:
+        readme_path = hf_hub_download(model_id, filename="README.md")
+        metadata = metadata_load(readme_path)
+        print(metadata)
+        return metadata
+    except requests.exceptions.HTTPError:
+        return None
+
+
+
+
+with app:
+    gr.Markdown(
+    """
+    # Compare Deep Reinforcement Learning Agents 🤖
+    
+    Type two models id you want to compare or check examples below.
+    """)
+    with gr.Row():
+      model1_input = gr.Textbox(label="Model 1")
+      model2_input = gr.Textbox(label="Model 2")
+    with gr.Row():
+      app_button = gr.Button("Compare models")
+    with gr.Row():
+      with gr.Column():
+        model1_name = gr.Markdown()
+        model1_video_output = gr.Video()
+        model1_score_output = gr.Textbox(label="Mean Reward +/- Std Reward")
+      with gr.Column():
+        model2_name = gr.Markdown()
+        model2_video_output = gr.Video()
+        model2_score_output = gr.Textbox(label="Mean Reward +/- Std Reward")
+
+    app_button.click(load_agent, inputs=[model1_input, model2_input], outputs=[model1_name,  model1_video_output, model1_score_output, model2_name, model2_video_output, model2_score_output])
+    
+    examples = gr.Examples(examples=[["sb3/a2c-AntBulletEnv-v0","sb3/ppo-AntBulletEnv-v0"],
+        ["ThomasSimonini/a2c-AntBulletEnv-v0", "sb3/a2c-AntBulletEnv-v0"],
+        ["sb3/dqn-SpaceInvadersNoFrameskip-v4", "sb3/a2c-SpaceInvadersNoFrameskip-v4"], 
+        ["ThomasSimonini/ppo-QbertNoFrameskip-v4","sb3/ppo-QbertNoFrameskip-v4"]],
+                           inputs=[model1_input, model2_input])
+
+    
+app.launch()