Enterprise Database Systems
Reinforcement Learning Fundamentals
Reinforcement Learning: Essentials
it_mlrlfndj_01_enus
Reinforcement Learning: Tools & Frameworks
it_mlrlfndj_02_enus
Reinforcement Learning: Essentials
Lesson Objectives
Reinforcement Learning: Essentials
- define reinforcement learning and describe its essential elements
- recognize the key differences between the reinforcement learning and machine learning paradigms
- depict the flow of reinforcement learning using agent, action, and environment
- describe different state change scenarios and transition processes in reinforcement learning
- recognize the role of rewards in reinforcement learning
- list the essential steps agents take to make decisions in reinforcement learning
- recognize prominent reinforcement learning environment types
- install OpenAI Gym and OpenAI Universe
- list reinforcement learning elements, agents involved in the process and the steps they take, and reinforcement learning environments
Overview/Description
Explore reinforcement learning and its components, which can be used to help develop critical algorithms for decision making.
Target
Prerequisites: none
Reinforcement Learning: Tools & Frameworks
Lesson Objectives
Reinforcement Learning: Tools & Frameworks
- recognize the different types of reinforcement learning that can be implemented for decision-making
- implement reinforcement learning using Keras and Python
- identify the role of the Markov decision process in reinforcement learning
- describe Q-learning, Q-learning rule, and deep Q-learning
- install TensorFlow
- implement reinforcement learning using TensorFlow
- implement Q-learning using Python
- implement reinforcement learning using Python and TensorFlow and implement Q-learning using Python
Overview/Description
Discover reinforcement learning types and how to implement reinforcement learning using Keras, Python, and TensorFlow. Explore the concept of Q-learning and how to implement it using Python.
Target
Prerequisites: none