Live briefing
Everything about Policy gradient method
Class of reinforcement learning algorithms
Policy gradient methods are a class of reinforcement learning algorithms and a sub-class of policy optimization methods. Unlike value-based methods which learn a value function to derive a policy, policy optimization methods directly learn a policy function that selects actions without consulting a value function. For policy gradient to apply, the policy function is parameterized by a differentiable parameter. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Policy gradient methodA 5-minute orientation
- Skim a recent paper: Global Optimality Guarantees for Policy Gradient MethodsInfluential work since 2022
- Pick up a classic book: Decision Making HandbookThe most-reprinted book on the subject
- Read the landmark paper: Learning CPG-based biped locomotion with a policy gradient methodCited 81 times
- Go sideways: Proximal policy optimizationA closely related topic
- Go sideways: Actor-critic algorithmA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🏆 Landmark papers (most cited)
Learning CPG-based biped locomotion with a policy gradient method
Policy gradient methods
Virtual Synchronous Generator Control Using Twin Delayed Deep Deterministic Policy Gradient Method
A Collaborative Multiagent Reinforcement Learning Method Based on Policy Gradient Potential
Inverse design of grating couplers using the policy gradient method from reinforcement learning
Policy-based optimization: single-step policy gradient method seen as an evolution strategy
A multiagent deep deterministic policy gradient-based distributed protection method for distribution network
Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient Method and Global Convergence
🆕 Influential since 2022
Global Optimality Guarantees for Policy Gradient Methods
Adaptive Weighted Combination Approach for Wind Power Forecast Based on Deep Deterministic Policy Gradient Method
Research on Wargame Decision-Making Method Based on Multi-Agent Deep Deterministic Policy Gradient
Linear Convergence of a Policy Gradient Method for Some Finite Horizon Continuous Time Control Problems
AUV Collision Avoidance Planning Method Based on Deep Deterministic Policy Gradient
📚 Books worth reading
- 📕Decision Making HandbookJerry Ramonyai · 2022
Deep Reinforcement Learning Hands-OnMaxim Lapan · 2018
Intelligent Science and Intelligent Data EngineeringJian Yang · 2013
Neural networksSimon S. Haykin · 1994
Coding the MatrixPhilip N. Klein · 2013
Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and moreMaxim Lapan · 2018
Fundamentals of Deep LearningNikhil Buduma · 2017- 📕Parallel computing is everywhereItaly) ParCo (Conference) (2017 Bologna · 2018
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Proximal policy optimization Proximal policy optimization (PPO) is a reinforcement learning (RL) algorithm for training an intelligent agent. Specifically, it is a policy gradient…
- 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…
- Online machine learning In computer science, online machine learning is a method of machine learning in which data becomes available in a sequential order and is used to update…
- 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…
- Stochastic gradient Langevin dynamics Stochastic gradient Langevin dynamics (SGLD) is an optimization and sampling technique composed of characteristics from Stochastic gradient descent, a…
- 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…
- Quasi-Newton method In numerical analysis, a quasi-Newton method is an iterative numerical method used either to find zeroes or to find local maxima and minima of functions…
- 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…