EURASIP Journal on Wireless Communications and Networking

Table 2 Comparison of testing results with w_m=0.5 for all mobile users

From: Decentralized computation offloading for multi-user mobile edge computing: a deep reinforcement learning approach

	Average reward			Average power (watt)			Average delay (ms)
	*User 1*	*User 2*	*User 3*	*User 1*	*User 2*	*User 3*	*User 1*	*User 2*	*User 3*
DDPG	− 1.770	− 5.670	− 12.782	0.205	0.774	1.939	1.489	3.600	6.174
DQN	− 2.174	− 7.657	− 14.688	0.292	1.156	2.320	1.428	3.753	6.176
GD-Offload	− 2.514	− 7.597	− 18.690	0.402	1.309	3.143	1.007	2.103	5.951
GD-Local	− 1.633	− 9.504	− 20.071	0.216	1.678	3.407	1.106	2.228	6.072

Back to article page