wangshusen/DRL has 4,737 GitHub stars and 681 forks. GitHot measured +1 stars in 24 hours, +4 in 7 days, and +5 in 15 days. Last checked 2026-11-22 06:25 UTC. Last push 2022-12-10.
측정된 스타 증가
- in 24h
- +1
- in 7 days
- +4
- in 15 days
- +5
- in 1 month
- 기록 수집 중
서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.
소개
심층 강화 학습
학습README.md
OriginalDeep Reinforcement Learning
Overview.
Reinforcement Learning [slides] [lecture note] [Video (in Chinese)].
Value-Based Learning [slides] [Video (in Chinese)].
Policy-Based Learning [slides] [Video (in Chinese)].
Actor-Critic Methods [slides] [Video (in Chinese)].
AlphaGo [slides] [Video (in Chinese)].
TD Learning.
Sarsa [slides] [Video (in Chinese)].
Q-learning [slides] [Video (in Chinese)].
Multi-Step TD Target [slides] [Video (in Chinese)].
Advanced Topics on Value-Based Learning.
Experience Replay (ER) & Prioritized ER [slides] [Video (in Chinese)].
Overestimation, Target Network, & Double DQN [slides] [Video (in Chinese)].
Dueling Networks [slides] [Video (in Chinese)].
Policy Gradient with Baseline.
Policy Gradient with Baseline [slides] [Video (in Chinese)].
REINFORCE with Baseline [slides] [Video (in Chinese)].
Advantage Actor-Critic (A2C) [slides] [Video (in Chinese)].
REINFORCE versus A2C [slides] [Video (in Chinese)].
Advanced Topics on Policy-Based Learning.
Trust-Region Policy Optimization (TRPO) [slides] [Video (in Chinese)].
Partial Observation and RNNs.
Dealing with Continuous Action Space.
Discrete versus Continuous Control [slides] [Video (in Chinese)].
Deterministic Policy Gradient (DPG) for Continuous Control [slides] [Video (in Chinese)].
Stochastic Policy Gradient for Continuous Control [slides] [Video (in Chinese)].
Multi-Agent Reinforcement Learning.
Basics and Challenges [slides] [Video (in Chinese)].
Centralized VS Decentralized [slides] [Video (in Chinese)].
Imitation Learning.
Inverse Reinforcement Learning.
Generative Adversarial Imitation Learning (GAIL).
관련 프로젝트 살펴보기
불러오는 중…