September 2018
Intermediate to advanced
288 pages
7h 38m
English
In reverse reinforcement learning (IRL), the reward function is derived from the observed behavior. As we have learned, in reinforcement learning, we use rewards to learn the behavior of a particular system. In IRL, this function is reversed; in fact, the agent observes the behavior of the system to understand what goal it is trying to achieve.
In an IRL, problem we start from the following:
Based on this data, we determine the reward function that the agent is optimizing. An example of Inverse reinforcement learning applied in simple domains such as Atari games was released from ...
Read now
Unlock full access