concept exploitation in category reinforcement learning

This is an excerpt from Manning's book Grokking Deep Reinforcement Learning.
The reward received by the agent may be weak, in the sense that it may provide no supervision. The reward may indicate goodness and not correctness, meaning it may contain no information about other potential rewards. Thus the agent must be able to learn from evaluative feedback. Evaluative feedback gives rise to the need for exploration. The agent must be able to balance the gathering of information with the exploitation of current information. This is also referred to as the exploration vs. exploitation tradeoff.
Figure 1.10 The difficulty of the exploration vs. exploitation tradeoff
![]()
Figure 1.10 The difficulty of the exploration vs. exploitation tradeoff
![]()
The bottom line is very intuitive, exploitation is your goal, and exploration gives you information about obtaining your goal. You must gather information to reach your goals, that is clear. But, in addition to that, there are several ways to collect information, and that is where the challenge lies.

This is an excerpt from Manning's book Deep Reinforcement Learning in Action.
In the next chapter, we will dive right into the real meat of RL, covering many of the core concepts, such as the tradeoff between exploration and exploitation, Markov decision processes, value functions, and policies (these terms will make sense soon). But first, at the beginning of the next chapter we’ll introduce some of the teaching methods we’ll employ throughout the book.
When we first start playing, we need to play the game and observe the rewards we get for the various machines. We can call this strategy exploration, since we’re essentially randomly exploring the results of our actions. This is in contrast to a different strategy we could employ called exploitation, which means that we use our current knowledge about which machine seems to produce the most rewards, and keep playing that machine. Our overall strategy needs to include some amount of exploitation (choosing the best lever based on what we know so far) and some amount of exploration (choosing random levers so we can learn more). The proper balance of exploitation and exploration will be important to maximizing our rewards.