Everything about Reinforcement learning
Field of machine learning
In machine learning and optimal control, reinforcement learning (RL) is concerned with how an intelligent agent should take actions in a dynamic environment in order to maximize a reward signal. Reinforcement learning is one of the three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Reinforcement learningA 5-minute orientation
- Skim a recent paper: Deep Reinforcement Learning for Autonomous Driving: A SurveyInfluential work since 2022
- Pick up a classic book: Psychology of Learning and MotivationThe most-reprinted book on the subject
- Read the landmark paper: Human-level control through deep reinforcement learningCited 25,310 times
- Go sideways: Deep reinforcement learningA closely related topic
- Go sideways: Markov decision processA closely related topic
📖 Definitions
Noun : Learning that occurs through reinforcement, especially through rewards, encouragement, or other consequences that strengthen desired behaviours.
Noun A machine-learning paradigm in which a model or agent learns by taking actions and receiving reward signals that indicate how well those actions achieve a desired objective.
🏆 Landmark papers (most cited)
Human-level control through deep reinforcement learning
Reinforcement Learning: An Introduction
Reinforcement Learning: A Survey
Hierarchical Reinforcement Learning
Quantum Reinforcement Learning
Reinforcement Learning
Meta-learning in Reinforcement Learning
Relational Reinforcement Learning
🆕 Influential since 2022
📚 Books worth reading
Psychology of Learning and MotivationDouglas L. Medin · 1992
LearningFred Simmons Keller · 1954
Deterrents and reinforcementDouglas H. Lawrence · 1962
Reinforcement LearningRichard S. Sutton · 1992
Reinforcement and systemic machine learning for decision makingParag Kulkarni · 2012
Conditioning and learningErnest Ropiequet Hilgard, Donald George Marquis · 1940
Reinforcement learning and approximate dynamic programming for feedback controlFrank L. Lewis, Derong Liu · 2012
Motivated reinforcement learningKathryn E. Merrick · 2009
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- 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…
- Markov decision process In decision theory, a Markov decision process (MDP) is a mathematical model for sequential decision making when outcomes are uncertain. It is a type of…
- 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…
- Q-learning Q-learning is a reinforcement learning algorithm that trains an agent to assign values to its possible actions based on its current state, without requiring…
- Partially observable Markov decision process A partially observable Markov decision process (POMDP) is a generalization of a Markov decision process (MDP). A POMDP models an agent decision process…
- Multi-armed bandit In probability theory and machine learning, the multi-armed bandit problem (sometimes called the K- or N-armed bandit problem) is named from imagining…
- Bellman equation A Bellman equation, named after Richard E. Bellman, is a technique in dynamic programming which breaks an optimization problem into a sequence of simpler…
- Reinforcement learning from human feedback In machine learning, reinforcement learning from human feedback (RLHF) is a technique to align an intelligent agent with human preferences. It involves…