Advances, Systems and Applications
Notations | Definition |
---|---|
\(\beta\) | The hyperparameter of the entropy term |
\(\gamma\) | The discount factor |
\(N,\mathcal N\) | The number and set of edge clouds |
G | The video set through the XC scheme |
\(F,\mathcal F\) | The number and set of videos |
\(x_{t,n}^f\) | The variable whether the requested video f is transmitted from the remote cloud to edge cloud n at time t |
\(y_{t,n}^f\) | The variable whether the requested video f has been stored in edge cloud n at time t |
\(q_{t,n}^f\) | The request for file f received by the edge cloud n at time t |
C | The maximum capacity of edge cloud |
\({s}_{t,n}\) | The state of agent n at time t |
\(\hat{s}_{t,n}\) | The joint observation state of an agent n |
\(\pi _{t,n}\) | The policy of agent n |
\({a}_{t,n}\) | The action of agent n |
\({\omega }_{n}\) | The parameter of the critic network for agent n |
\(\theta _{n}\) | The parameter of the actor network for agent n |
\(R_{t,n}\) | The expected value equation for edge cloud n |
\(r_{n}\) | The global reward |
B | The replay buffer memory |
\(\zeta\) | The target network update parameter n |
V | The value function of the critic network |
\(\tilde{A}_{t, n}\) | The advantage function |
\(\mathcal N_n\) | The neighborhoods set of agent n |