New answers tagged policy-gradients
0
votes
experience replay memory: saving the next state required when state does not depend on action?
For question one; if you look at Q-learning for example the next state is retrieved from the replay buffer and used in value estimation / loss calculation during critic training:
...
Top 50 recent answers are included
Related Tags
policy-gradients × 60reinforcement-learning × 54
machine-learning × 13
deep-learning × 12
actor-critic × 9
neural-network × 7
python × 4
tensorflow × 4
pytorch × 4
mathematics × 3
q-learning × 3
dqn × 3
cost-function × 3
nlp × 2
loss-function × 2
optimization × 2
supervised-learning × 2
gpu × 2
implementation × 2
ai × 2
derivation × 2
cnn × 1
rnn × 1
gradient-descent × 1
backpropagation × 1