Spaces:
Sleeping
Sleeping
Readme updated
Browse files
README.md
CHANGED
|
@@ -57,7 +57,7 @@ We built the **AI-Kinetic Disaster Recovery Grid** — a Multi-Agent Reinforceme
|
|
| 57 |
|
| 58 |
The world is modeled as a 5×5 matrix using `openenv-core`. Each sector tracks internal state: **Health**, **Power**, and **Risk**.
|
| 59 |
|
| 60 |
-

|
|
@@ -86,20 +86,20 @@ trainer.train()
|
|
| 86 |
|
| 87 |
Before pushing to the Hugging Face Space, we validate agent logic and entropy sequences via a local CLI built on `openenv-core` for rapid debugging of the 5×5 grid state transitions.
|
| 88 |
|
| 89 |
-
|
| 90 |
|
| 91 |
-
▶ [Watch
|
| 92 |
|
| 93 |
-

|
| 97 |
|
| 98 |
To visualize multi-agent orchestration, we built a web-based UI — the **Operational Theatre** — deployed on Hugging Face Spaces. It allows random anomaly injection while observing LLM-powered agents respond in real time.
|
| 99 |
|
| 100 |
-
|
| 101 |
|
| 102 |
-
▶ [Watch
|
| 103 |
|
| 104 |
*HF Space UI showing the autonomous agent navigating the grid with the Agent Brain Log streaming reasoning.*
|
| 105 |
|
|
|
|
| 57 |
|
| 58 |
The world is modeled as a 5×5 matrix using `openenv-core`. Each sector tracks internal state: **Health**, **Power**, and **Risk**.
|
| 59 |
|
| 60 |
+

|
| 61 |
*VS Code showing `environment.py` defining the `CityGrid` class and episode dynamics.*
|
| 62 |
|
| 63 |
### 2. Training Scripts (GRPO + Unsloth)
|
|
|
|
| 86 |
|
| 87 |
Before pushing to the Hugging Face Space, we validate agent logic and entropy sequences via a local CLI built on `openenv-core` for rapid debugging of the 5×5 grid state transitions.
|
| 88 |
|
| 89 |
+
<video controls src="./Vrxpe4DR6s.mp4" width="100%"></video>
|
| 90 |
|
| 91 |
+
▶ [Watch validation video](./Vrxpe4DR6s.mp4)
|
| 92 |
|
| 93 |
+

|
| 94 |
*Local terminal simulator showing a completed 50-step sequence tracking City Health and Energy metrics.*
|
| 95 |
|
| 96 |
### Live Agent Simulation (Operational Theatre)
|
| 97 |
|
| 98 |
To visualize multi-agent orchestration, we built a web-based UI — the **Operational Theatre** — deployed on Hugging Face Spaces. It allows random anomaly injection while observing LLM-powered agents respond in real time.
|
| 99 |
|
| 100 |
+
<video controls src="./opera_Z2g5nn07sJ.mp4" width="100%"></video>
|
| 101 |
|
| 102 |
+
▶ [Watch operational theatre video](./opera_Z2g5nn07sJ.mp4)
|
| 103 |
|
| 104 |
*HF Space UI showing the autonomous agent navigating the grid with the Agent Brain Log streaming reasoning.*
|
| 105 |
|