Spaces:
Sleeping
Sleeping
Andrei Cozma
commited on
Commit
·
f49bb60
1
Parent(s):
6e58943
Updates
Browse files
README.md
CHANGED
@@ -31,7 +31,9 @@ Install all the dependencies using `pip`:
|
|
31 |
|
32 |
# 2. Interactive Demo
|
33 |
|
34 |
-
|
|
|
|
|
35 |
|
36 |
```bash
|
37 |
❯ python3 demo.py
|
@@ -42,7 +44,7 @@ Running on local URL: http://127.0.0.1:7860
|
|
42 |
|
43 |
# 2. Agents
|
44 |
|
45 |
-
## Dynamic-Programming Agent
|
46 |
|
47 |
TODO
|
48 |
|
@@ -52,7 +54,7 @@ TODO
|
|
52 |
TODO
|
53 |
```
|
54 |
|
55 |
-
## Monte-Carlo Agent
|
56 |
|
57 |
This is the implementation of an On-Policy Monte-Carlo agent to solve several toy problems from the OpenAI Gymnasium.
|
58 |
|
|
|
31 |
|
32 |
# 2. Interactive Demo
|
33 |
|
34 |
+
HuggingFace Space: [acozma/CS581-Algos-Demo](https://huggingface.co/spaces/acozma/CS581-Algos-Demo)
|
35 |
+
|
36 |
+
Launch the Gradio demo web app locally:
|
37 |
|
38 |
```bash
|
39 |
❯ python3 demo.py
|
|
|
44 |
|
45 |
# 2. Agents
|
46 |
|
47 |
+
## 2.1. Dynamic-Programming Agent
|
48 |
|
49 |
TODO
|
50 |
|
|
|
54 |
TODO
|
55 |
```
|
56 |
|
57 |
+
## 2.2. Monte-Carlo Agent
|
58 |
|
59 |
This is the implementation of an On-Policy Monte-Carlo agent to solve several toy problems from the OpenAI Gymnasium.
|
60 |
|
demo.py
CHANGED
@@ -298,7 +298,7 @@ def run(policy_fname, n_test_episodes, max_steps, render_fps, epsilon):
|
|
298 |
|
299 |
with gr.Blocks(title="CS581 Demo") as demo:
|
300 |
gr.components.HTML(
|
301 |
-
"<h1>CS581 Final Project Demo - Dynamic Programming & Monte-Carlo RL Methods</h1>"
|
302 |
)
|
303 |
|
304 |
gr.components.HTML("<h2>Select Configuration:</h2>")
|
|
|
298 |
|
299 |
with gr.Blocks(title="CS581 Demo") as demo:
|
300 |
gr.components.HTML(
|
301 |
+
"<h1>CS581 Final Project Demo - Dynamic Programming & Monte-Carlo RL Methods (<a href='https://huggingface.co/spaces/acozma/CS581-Algos-Demo'>HF Space</a>)</h1>"
|
302 |
)
|
303 |
|
304 |
gr.components.HTML("<h2>Select Configuration:</h2>")
|