How deeply does Introduction to Generative AI, Second Edition cover reinforcement learning?

Defines rewards, penalties, and comparison paradigms at an intuitive level, but stops short of algorithmic or implementation detail.

Reinforcement learning

As explained in Introduction to Generative AI, Second Edition

Reinforcement learning is machine learning in which an agent learns behavior from rewards or penalties produced by interactions with an environment.

Reinforcement learning is machine learning by trial and error. An agent interacts with an environment, receives rewards or penalties, and gradually favors behaviors associated with better results. section 1.1

It differs from other learning paradigms in what guides improvement:

Supervised learning maps labeled inputs to known outputs. section 1.1
Unsupervised learning discovers patterns without labels or a specific reward. section 1.1

A reward is numerical feedback representing progress toward a task. Positive feedback makes rewarded behavior more likely to recur, while penalties make the associated behavior less likely. The approach is useful when a system can evaluate results, but desirable behavior is not always easy to define. section 1.1 section 2.10

Reinforcement learning from human feedback

For large language models, people evaluate responses as acceptable, problematic, or preferable. Those judgments estimate a reward function, allowing later responses to improve according to aggregated human preferences. This method, called reinforcement learning from human feedback (RLHF), helps guide behavior when no simple automatic reward function exists. section 2.10

How Introduction to Generative AI, Second Edition covers it

Cover of Introduction to Generative AI, Second Edition

liveBook manning.com

Read Introduction to Generative AI, Second Edition on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Reinforcement Learning from Human FeedbackReinforcement learning is a machine learning paradigm in which an agent learns behavior by optimizing rewards obtained through interaction with an environment.
liveBook manning.com

Optimization Algorithms: AI techniques for design, planning, and control problemsReinforcement learning is a machine-learning paradigm in which an agent learns action policies from interactions and evaluative feedback.
liveBook manning.com

Evolutionary Deep Learning: Genetic algorithms and neural networksReinforcement learning is a machine-learning paradigm in which an agent learns behavior by interacting with an environment and receiving rewards or other evaluative feedback.
liveBook manning.com

Sutskever's ListMachine learning in which an agent learns behavior through rewards or penalties from interaction with an environment.
liveBook manning.com

Deep Learning with R, Third EditionReinforcement learning is a machine-learning technique in which an agent learns behavior through interaction with an environment and feedback such as rewards.
liveBook manning.com

Build a Robo-Advisor with Python (From Scratch)Reinforcement learning is a machine-learning approach in which an agent learns a decision policy through interactions with an environment and feedback from rewards or penalties.
liveBook manning.com

Grokking AI Algorithms, Second EditionReinforcement learning is a machine-learning paradigm in which an agent learns behavior through rewards for useful actions and penalties for harmful or unsuccessful actions in an environment.
liveBook manning.com

The AI Pocket BookA learning approach in which an agent improves by trying actions and using feedback from the results.
liveBook manning.com

Build a Reasoning Model (From Scratch)A training approach where a model learns from rewards or feedback to improve its behavior.
liveBook manning.com

Grokking AI ApplicationsReinforcement learning is a machine learning approach in which an agent learns through trial and error while interacting with an environment to achieve goals.
liveBook manning.com

Deep Learning with Python, Third EditionA learning setup where an agent improves by interacting with an environment and receiving feedback, used here as a way to keep generating fresh training problems for LLMs.
liveBook manning.com

Grokking Machine LearningA machine-learning approach in which an agent learns to choose actions by interacting with an environment and receiving rewards or punishments.
liveBook manning.com

Acing the CCNA Exam: Volume 2 Advanced Networking and SecurityReinforcement learning is a machine-learning approach in which an agent learns behavior through interactions with an environment and feedback about its actions.
liveBook manning.com

Causal AIA machine-learning paradigm in which an agent learns actions or policies by interacting with an environment and receiving rewards or penalties.
liveBook manning.com

Inside AIReinforcement learning is a machine-learning technique in which an agent learns behavior by interacting with an environment and receiving feedback for its actions.
liveBook manning.com

Data Without LabelsA machine-learning paradigm in which an agent improves its behavior through sequential interactions, trial and error, and feedback from rewards or penalties.
liveBook manning.com

Data-Driven CybersecurityReinforcement learning is a machine-learning approach in which an agent learns decisions by interacting with an environment and optimizing cumulative feedback.

Compare how 18 books explain reinforcement learning →

Related concepts

reward signaluses · A reward signal is an evaluative feedback value representing the desirability or payoff of an action, outcome, or state.
machine learningkind of · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
AI agentuses · An AI agent is a computational system that uses artificial intelligence to interpret information, select actions, and pursue goals through interaction with an environment.
environmentuses · An environment is the external context, including its entities and conditions, in which a system, process, or agent exists or operates.
reinforcement learning with human feedbackused by · Reinforcement learning with human feedback is a model-training approach that uses human evaluations or preferences to guide optimization of model behavior.
fine-tuningcontrasts with · Fine-tuning is adapting a pretrained machine-learning model by training it further on targeted data or objectives for a task, domain, or behavior.

This explainer was generated by Manning's knowledge graph from the text of Introduction to Generative AI, Second Edition. The section links point to the parts of the book it draws on.