Roh's Warehouse

Home

โฏ

Posts

โฏ

Papers

โฏ

(2020) Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

(2020) Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

Properties1
tagsai-scheduling

Graph View

  • 1. ๋ฌธ์ œ ํ‘œํ˜„: disjunctive graph (๊ฐ„๋žตํžˆ)
  • 2. MDP ์„ค๊ณ„: ๋””์ŠคํŒจ์นญ์„ ์ˆœ์ฐจ์  ์˜์‚ฌ๊ฒฐ์ •์œผ๋กœ
  • 3. ์ƒํƒœ๋ฅผ ๋ฒกํ„ฐ๋กœ: GIN ๊ธฐ๋ฐ˜ GNN (์ค‘๊ฐ„ ๋ถ„๋Ÿ‰)
  • 4. PPO: ์ •์ฑ…์„ ์–ด๋–ป๊ฒŒ ํ•™์Šตํ•˜๋Š”๊ฐ€ (๊ฐ€์žฅ ์ž์„ธํžˆ)
  • 4.1 ์ถœ๋ฐœ์ : Policy Gradient
  • 4.2 ๋ถ„์‚ฐ์„ ์ค„์ด๊ธฐ: Actor-Critic๊ณผ Advantage
  • 4.3 On-policy์˜ ํ•จ์ •๊ณผ ์‹ ๋ขฐ์˜์—ญ(TRPO)
  • 4.4 PPO: ์‹ ๋ขฐ์˜์—ญ์„ 1์ฐจ ์ตœ์ ํ™”๋กœ ๋‹จ์ˆœํ™”
  • 4.5 Entropy bonus์™€ ์ „์ฒด loss
  • 4.6 ์™œ ํ•˜ํ•„ PPO์ธ๊ฐ€
  • 5. ์‹คํ—˜ ๊ฒฐ๊ณผ (๊ฐ„๋‹จํžˆ)
  • 6. ํ•œ๊ณ„์™€ ์˜์˜
  • ์ฐธ๊ณ ๋ฌธํ—Œ

Backlinks

  • 38. ์‚ฌ๋ก€ ์—ฐ๊ตฌ: RL ๊ธฐ๋ฐ˜ FAB ๋””์ŠคํŒจ์นญ ์—ฐ๊ตฌ ํ๋ฆ„
  • (2024) A Survey on Interpretable Reinforcement Learning
  • (2025) Design Patterns of Deep Reinforcement Learning Models for Job Shop Scheduling Problems

Created with Quartz v5.0.0 ยฉ 2026

  • GitHub
  • Discord Community