July 2018
Intermediate to advanced
254 pages
8h 12m
English
The next step is to perform what are called rollouts using the current policy of the agent to collect n number of transitions. This process is basically letting the agent interact with the environment and generating new experiences in terms of state transitions, usually represented as a tuple containing the state, action, reward obtained, and next state, or in short (
,
,
, ), as illustrated ...
Read now
Unlock full access