New answers tagged ddpg
2
generally the approach is to have a separate head. For example, imagine you have latent vector $z_k$, you would output two values: $h(z_k)$ and $f(z_k)$ where $0 \leq h \leq 1$ and $b_0 \leq f \leq b_1$ where $b_0$ and $b_1$ are your bounds.
In thios setup, during inference you would check $h_k$ and if its greater than some threshold (usually .5), youd ...
0
You are right, it is sloppy notation by the authors. However, the target network is not necessarily linked to the behaviour policy $\beta$ either.
Essentially when they take the expectation with respect to $\rho^\beta$ they are taking expectation with respect to a state distribution induced by some policy $\beta$ that is not necessarily the same as our ...
Top 50 recent answers are included
Related Tags
ddpg × 51reinforcement-learning × 46
deep-rl × 19
policy-gradients × 13
deep-learning × 5
actor-critic-methods × 5
tensorflow × 4
keras × 4
dqn × 4
neural-networks × 3
python × 3
rewards × 3
gym × 3
experience-replay × 3
control-problem × 3
continuous-action-spaces × 3
machine-learning × 2
q-learning × 2
papers × 2
algorithm × 2
markov-decision-process × 2
pytorch × 2
open-ai × 2
environment × 2
off-policy-methods × 2