Investigating the Effects of Hyperparameters in Quantum-Enhanced Deep Reinforcement Learning

Table 3

The method of calculating the expectation value for action selection (this is the assumption).

Total number of repeated measurements	500	500	500	500
Total number of measurements which gives 1	330	400	350	190
Total number of measurements which gives 0	170	100	150	310
Probability of getting 1 or P (1)	0.66	0.8	0.7	0.38
Probability of getting 0 or P (0)	0.34	0.2	0.3	0.62
Expectation value	0.66	0.8	0.7	0.62