Live briefing
Everything about Reinforcement learning from human feedback
Machine learning technique
In machine learning, reinforcement learning from human feedback (RLHF) is a technique to align an intelligent agent with human preferences. It involves training a reward model to represent preferences, which can then be used to train other models through reinforcement learning. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Reinforcement learning from human feedbackA 5-minute orientation
- Skim a recent paper: Deep preference learning for multiple criteria decision analysisInfluential work since 2022
- Pick up a classic book: Learning mechanisms in food selectionThe most-reprinted book on the subject
- Read the landmark paper: Modelling Human Decision Behaviour with Preference LearningCited 63 times
- Go sideways: Reinforcement learningA closely related topic
- Go sideways: Deep reinforcement learningA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Modelling Human Decision Behaviour with Preference Learning
Preference Learning in Consecutive Experimental Auctions
Learning conditional preference networks
Preference Learning and Demand Forecast
OPPORTUNITY AND PREFERENCE LEARNING
Preference Uncertainty, Preference Learning, and Paired Comparison Experiments
Model-Free Preference-Based Reinforcement Learning
Model-Based Learning from Preference Data
🆕 Influential since 2022
Deep preference learning for multiple criteria decision analysis
Extracting medicinal chemistry intuition via preference machine learning
A reinforcement learning approach for thermostat setpoint preference learning
Preference learning based deep reinforcement learning for flexible job shop scheduling problem
Consumer preference analysis: Diverse preference learning with online ratings
📚 Books worth reading
Learning mechanisms in food selectionLewis M. Barker, Michael P. Domjan · 1977- 📕Personality characteristics and learning style preferences of adult basic education studentsAnthony V. Manzo · 1975
- 📕Lernpsychologie der MarkenwahlArnulf Krais · 1977
Experimental assessments and clinical applications of conditioned food aversionsNorman S. Braveman · 1985
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Reinforcement learning In machine learning and optimal control, reinforcement learning (RL) (also known as approximate dynamic programming) is concerned with how an intelligent…
- Deep reinforcement learning Deep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem…
- Reward hacking Reward hacking or specification gaming occurs when an AI trained with reinforcement learning optimizes an objective function—achieving the literal, formal…
- Proximal policy optimization Proximal policy optimization (PPO) is a reinforcement learning (RL) algorithm for training an intelligent agent. Specifically, it is a policy gradient…
- Model-free (reinforcement learning) In reinforcement learning (RL), a model-free algorithm is an algorithm which does not estimate the transition probability distribution (and the reward…
- AI alignment In the field of artificial intelligence (AI), alignment aims to steer AI systems toward a person's or group's intended goals, preferences, or ethical principles…
- Actor-critic algorithm The actor-critic algorithm (AC) is a family of reinforcement learning (RL) algorithms that combine policy-based RL algorithms such as policy gradient methods…
- Reasoning model Reasoning language models (RLMs) or large reasoning models (LRMs) are large language models that are trained to solve tasks that require several steps…