Glossary term
Glossary term
Agentic Systems
In reinforcement learning, the parameter values that describe the current configuration of the environment, which the agent uses to choose an action.
Created for this library
A logistics RL team encodes vehicle location, current load, and time of day as the state for its dispatching agent.
A trading research team encodes recent price history and order-book features as the state for its execution agent.
An energy company encodes building temperature, occupancy, and outdoor conditions as the state for its HVAC RL agent.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License