Real-world uses

Created for this library

1. 1.

   A logistics RL team uses a state-action value function to estimate the long-run reward of dispatching to each candidate next stop.

2. 2.

   A trading research team uses a state-action value function to estimate the long-run revenue of each bid action in a market state.

3. 3.

   An energy company uses a state-action value function to estimate the value of each HVAC setpoint change in a building state.