Tactical decision-making through reinforcement learning with uncertainty estimation
AssigneeVolvo Autonomous Solutions AB
InventorsCarl-Johan HOEL, Leo LAINE
Life of this patent
Estimating the term…
Loading patent…
AssigneeVolvo Autonomous Solutions AB
InventorsCarl-Johan HOEL, Leo LAINE
Estimating the term…
A method of controlling an autonomous vehicle using a reinforcement learning, RL, agent. The method includes a plurality of training sessions, in which the RL agent interacts with an environment including the autonomous vehicle, each training session having a different initial value and yielding a state-action value function Qk(s, a) dependent on state and action; decision-making, in which the RL agent outputs at least one tentative decision relating to control of the autonomous vehicle; uncertainty estimation on the basis of a variability measure for the plurality of state-action value functions evaluated for a state-action pair corresponding to each of the tentative decisions; and vehicle control, wherein the at least one tentative decision is executed in dependence of the estimated uncertainty.
A method of controlling an autonomous vehicle using a reinforcement learning, RL, agent, the method comprising:
An arrangement for controlling an autonomous vehicle, comprising:
Dependencies are inferred from the claim text.