April 2018
Intermediate to advanced
334 pages
10h 18m
English
The reason behind the inefficiency of all the previous approaches is because the decision making happens in real time, where the state-action spaces are huge and continuous. The previous approaches were efficient under limited conditions as they were not able to fulfill all of the following conditions:
In order to cover the large state-action spaces, a large number of rules would be required in the solution base. Moreover, no exploration strategy is there to find an optimal solution. Thus, these traditional AI approaches found it difficult because of all the previously mentioned ...