Live briefing
Everything about Actor-critic algorithm
Reinforcement learning algorithms
The actor-critic algorithm (AC) is a family of reinforcement learning (RL) algorithms that combine policy-based RL algorithms such as policy gradient methods, and value-based RL algorithms such as value iteration, Q-learning, SARSA, and TD learning. Wikipedia →
🧠Start here: a 6-step reading path
- Read the overview: Actor-critic algorithmA 5-minute orientation
- Skim a recent paper: Smart Online Charging Algorithm for Electric Vehicles via Customized Actor–Critic LearningInfluential work since 2022
- Pick up a classic book: Reputational Crisis ManagementThe most-reprinted book on the subject
- Read the landmark paper: Natural actor–critic algorithmsCited 390 times
- Go sideways: Policy gradient methodA closely related topic
- Go sideways: Temporal difference learningA closely related topic
đź“– Definitions
No dictionary entry for this exact phrase.
🏆 Landmark papers (most cited)
Natural actor–critic algorithms
An actor-critic algorithm for constrained Markov decision processes
Impedance Learning for Robotic Contact Tasks Using Natural Actor-Critic Algorithm
A bounded actor–critic reinforcement learning algorithm applied to airline revenue management
On Finite-Time Convergence of Actor-Critic Algorithm
A soft actor-critic reinforcement learning algorithm for network intrusion detection
Energy optimization management of microgrid using improved soft actor-critic algorithm
Large-scale UAV swarm confrontation based on hierarchical attention actor-critic algorithm
🆕 Influential since 2022
Smart Online Charging Algorithm for Electric Vehicles via Customized Actor–Critic Learning
Optimal fractional-order PID controller based on fractional-order actor-critic algorithm
Soft Actor–Critic Algorithm Featured Residential Demand Response Strategic Bidding for Load Aggregators
Workflow scheduling based on asynchronous advantage actor–critic algorithm in multi-cloud environment
6D (2,0) bootstrap with the soft-actor-critic algorithm
đź“š Books worth reading
Reputational Crisis ManagementChavdar HristovPetar Kardzhilov, Plamen Atanasov, Hristina Slavova, Kalin Kalinov, Boyan Georgiev, Ina Bacheva, Milena Tsvetkova · 2017
Algorithms for reinforcement learningCsaba Szepesvári · 2010
Fundamentals of Deep LearningNikhil Buduma · 2017
The Dissemination and Evolution of Excellent Traditional Chinese Culture (ETCC) in the Age of Artificial Intelligence (AI)You Chen · 2026
International encyclopedia of human geographyN. J. Thrift, Rob Kitchin · 2009
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
đź”— Related topics
- Policy gradient method Policy gradient methods are a class of reinforcement learning algorithms and a sub-class of policy optimization methods. Unlike value-based methods which…
- Temporal difference learning Temporal difference (TD) learning refers to a class of model-free reinforcement learning methods which learn by bootstrapping from the current estimate…
- Reinforcement learning In machine learning and optimal control, reinforcement learning (RL) (also known as approximate dynamic programming) is concerned with how an intelligent…
- 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…
- Automatic basis function construction In machine learning, automatic basis function construction, also known as basis discovery, is a technique that finds a set of general-purpose (task-independent)…
- Batch normalization In artificial neural networks, batch normalization (also known as batch norm) is a normalization technique used to make training faster and more stable…
- 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…