sanjithp-dev commited on
Commit
4dd47dc
·
verified ·
1 Parent(s): 2481263

Readme updated

Browse files
Files changed (1) hide show
  1. README.md +6 -6
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
- ![OpenEnv Local Development Configuration](./assets/environment_config.jpeg)
61
  *VS Code showing `environment.py` defining the `CityGrid` class and episode dynamics.*
62
 
63
  ### 2. Training Scripts (GRPO + Unsloth)
@@ -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
- ![Local CLI Validation Demo](./assets/validation_demo.gif)
90
 
91
- ▶ [Watch full validation video](./assets/validation_video.mp4)
92
 
93
- ![Local Terminal Simulation Output](./assets/terminal_output.jpeg)
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
- ![Operational Theatre Demo](./assets/operational_demo.gif)
101
 
102
- ▶ [Watch full operational theatre video](./assets/operational_theatre.mp4)
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
+ ![OpenEnv Local Development Configuration](./Cursor_iz08V4mFrU.png)
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
+ ![Local Terminal Simulation Output](./warp_D3ZKOqiyfq.png)
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