Figure 12

Training and evaluation metric plots for the RL agent using the A2C algorithm. (a,b) show the Mean and Standard Deviation of âtree_scoreâ. (c,d) display the Mean and Standard Deviation of âisTreeCorrectlyAnsweredâ. (e,f) present the Mean and Standard Deviation of âisTreeAdditionalDataRequestedâ. (g,h) show the Mean and Standard Deviation of âisTreeWronglyAnsweredâ.