Update README.md

README.md

@@ -152,5 +152,13 @@ Once pulled, sanity-check locally with ollama run deepseek-r1:7b, then in anothe
 After the LLM endpoint is up, you can proceed to the inference server step to bind the persona/prompt layer to RTG conditioning and the control loop in one end to end pipeline.
 
 7) Inference 
-
-8) Deployment on a real building using cloud server and edge device
+During inference, we deploy Gen-HVAC as a stateless HTTP microservice
+
+ that loads the trained Decision Transformer checkpoint and normalization statistics at startup, maintains a short autoregressive context window internally,
+ and returns multi-zone heating/cooling setpoints per control step. 
+ In our experiments, EnergyPlus/Sinergym executes inside the Docker container, while the inference service runs on the host/server (CPU/GPU), 
+ so the simulator can stream observation vectors to POST /predict (payload: {step, obs, info}) and receive an action vector in the response, with POST /reset 
+ used to clear policy history at episode boundaries. 
+ 
+ When enabled, the DHIL module queries a local Ollama endpoint and updates the comfort RTG target at a low frequency (e.g., every 4 steps).
+