New answers tagged

1 vote

In policy gradient methods why do we compute the gradient of the objective function through a one-trajectory estimate?

Sutton & Barto's book of Reinforcement Learning mentions below: When the state-value function is used to assess actions in this way it is called a critic, and the overall policy-gradient method ...
Double Knot's user avatar
1 vote
Accepted

In policy gradient methods why do we compute the gradient of the objective function through a one-trajectory estimate?

The one-trajectory sample is the Monte-Carlo way to estimate the gradient, which, turns out, to be an unbiased estimator although with high-variance due to relying only on one sample: I think this is ...
Luca Anzalone's user avatar

Top 50 recent answers are included