New answers tagged policy-gradients
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 ...
- 950
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 ...
- 2,493
Top 50 recent answers are included