Business↗
Policy Search, Policy Gradients and Actor-Critic Methods
A practical guide to directly optimising decision policies using parameterised policy search, gradient estimation, actor-critic architectures and stable optimisation practices.
Every page in the KEVOS library tagged policy search. 2 pages.
A practical guide to directly optimising decision policies using parameterised policy search, gradient estimation, actor-critic architectures and stable optimisation practices.
Searching directly in the space of parameterised decision rules — evaluating policies by simulation and optimising them without computing state values.