Reinforcement learning finds the agent’s optimal behavior in a specific situation. This technique is able to adapt to environmental changes for real world business applications for example. In reinforcement learning I use the cost function to develop the policy. In inverse reinforcement learning I use the policy to develop the cost function.

My new books on Amazon
Distributed Artificial Intelligence for Classical and Quantum Computers by Zahra M.M.A. Sadiq
Knowledge Engineering. Artificial Intelligence and Legal Logic by Zahra M.M.A. Sadiq
Computer Music. Electronica, Algorithms, Artificial Intelligence by Zahra M.M.A. Sadiq
The Gifted Individual and the Right to Education by Zahra M.M.A. Sadiq
[ Ссылка ]

Patreon
[ Ссылка ]

свернуть