Solving a Joint Pricing and Inventory Control Problem for Perishables via Deep Reinforcement Learning

Table 3

Results for dynamic pricing with positive lead time.

Method	Lifetime
PAQ-DQN	2	3242.104	2911.139	254.905	291.997
	3	4734.766	4455.814	40.439	110.146
	4	4840.443	4714.712	34.066	28.642
PAQ-A2C	2	3081.546	2305.394	232.000	573.749
	3	4513.786	4474.915	207.470	130.278
	4	4919.332	2278.324	49.802	748.916