Reinforcement Learning: Machine Learning Category

142
Reinforcement_Machine_Learning_Algorithm_Explained
Reinforcement_Machine_Learning_Algorithm_Explained

[editorskit display=”wordcount” before=”Reading Time: ” after=” min”]

Reinforcement learning is another algorithm category in machine learning where it continuously improves its model by leveraging feedback from previous iteration unlike supervised learning and unsupervised learning. Reinforcement learning is used in those cases where algorithms are set to train the model through continuous learning. The performance criteria of standard reinforcement learning model is measurable where outputs are not tagged rather graded. The self-driving vehicles shall have a positive score while avoiding a crash.

Reinforcement learning can be complicated and can probably be best explained through an analogy to a video game. As a player advances through a virtual environment, they learn various actions under different conditions and become more familiar with the game play. These learned actions and values then influence the player’s subsequent behaviour and their performance immediately improves based on their learning and past experience. This is an ongoing process. An example of specific algorithm in reinforcement learning is Q-learning where you start with a set of environment of states.

LEAVE A REPLY

Please enter your comment!
Please enter your name here