Dueling Network Architectures for Deep Reinforcement Learning

arxiv:1511.06581

Original source · Paper JSON

Reinforcement learning · 2015-11-20

Cites (2) · Cited by (7)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3

Contents

• Dueling Network Architectures for Deep Reinforcement Learning
• Abstract
• 1 Introduction
• 1.1 Related Work
• 2 Background
• 2.1 Deep Q-networks
• 2.2 Double Deep Q-networks
• 2.3 Prioritized Replay
• 3 The Dueling Network Architecture
• 4 Experiments
• 4.1 Policy evaluation
• 4.2 General Atari Game-Playing
• 5 Discussion
• 6 Conclusions
• Appendix A Double DQN Algorithm
• Instructions for reporting errors