Table 2.

Performance metrics for goal-oriented tasks: move-to-goal steps, time elapsed, mean reward, and standard deviation of rewards.

Move to Goal Steps	Time Elapsed (s)	Mean Reward	Std. of Rewards
Step: 10,000	55.449	−0.877	0.447
Step: 20,000	85.770	−0.093	0.787
Step: 30,000	117.238	0.323	0.857
Step: 40,000	148.027	0.691	0.599
Step: 50,000	179.527	0.578	0.645
Step: 60,000	210.429	0.704	0.539
Step: 70,000	241.473	0.707	0.552
Step: 80,000	272.897	0.680	0.578
Step: 90,000	304.707	0.708	0.569
Step: 100,000	336.163	0.863	0.432
Step: 200,000	656.214	0.983	0.129
Step: 300,000	982.363	0.989	0.146
Step: 400,000	1319.801	0.990	0.121
Step: 500,000	1671.575	1.000	0.000