Jeff Liu Lab
HomeProjectsWorkshopAI WikiAI LabShop
Sign In
All
Computing Science
Artificial Intelligence
Deep Learning
Reinforcement Learning
AI Agents
Embodied Intelligence
Robot Engineering
Human-Like Intelligence
AI Engineering
← Back to Wiki
Reinforcement Learning
RL Landscape
RL Milestones

Comments (0)

Sign in to comment

Table of Contents
Overview1. Markov Decision Process (MDP)1.1 Basic Framework1.2 Core Objective1.3 Bellman Equations1.4 MDP Extensions2. RL Taxonomy2.1 Overall Taxonomy Tree2.2 Model-Free vs Model-Based2.3 On-Policy vs Off-Policy2.4 Offline Reinforcement Learning2.5 Single-Agent vs Multi-Agent3. Key Algorithm Map3.1 By Development Timeline3.2 By Application Scenario4. Core Components of Deep RL4.1 Function Approximation4.2 Key Techniques for Stable Training4.3 Exploration Strategies5. Connection to LLM Post-Training5.1 RLHF Pipeline5.2 Beyond RLHF5.3 LLM from an RL Perspective6. Frontier Directions6.1 Current Hot Topics6.2 Open Challenges7. Suggested Learning PathReferencesFurther Reading

© 2026 Jeff Liu Lab. All rights reserved.

AboutPricingPrivacy & TermsContact