Study Log (2020.02)

2020-02-21

• multi_step_actor
  • simple_actor_test.py
    • rl/simple_action_actor.py
    • rl/brain.py
    • rl/QAgent.py
    • optim/RAam.py
  • Debug로 코드 따라가며 이해하기

---

2020-02-20

• 모두를 위한 RL강좌
  • Lecture #19
  • Lecture #20
• S-K RL
  • 소스코드 업데이트 및 환경 구축
    • Mac에서 Tree 구조 출력 필요시 다음 명령어로 설치 필요

      brew install tree
      

  • rl_networks.py
    • class NaiveActor(torch.nn.Module):
      • machine, batch 컨디션 체크 후 node_indices return
    • class NaiveCritic(torch.nn.Module):
      • critic_updater 레이어에서 node_doable 한 인덱스의 평균 return
• multi_step_actor
  • simple_actor_test.py
    • rl/mlp.py
    • rl/simple_action_brain.py
    • memory/simple_memory.py

---

2020-02-19

• 모두를 위한 RL강좌
  • Lecture #13
  • Lecture #14
  • Lecture #15
  • Lecture #16) Lab 7-2: DQN 2 (Nature 2015)
  • Lecture #17
  • Lecture #18

---

2020-02-18

• 모두를 위한 RL강좌
  • Lecture #10
  • Lecture #11
  • Lecture #12) Lab 6-1: Q Network for Frozen Lake
• 팡요랩
  • Lecture #10

---

2020-02-17

• 모두를 위한 RL강좌
  • Lecture #6
  • Lecture #7
  • Lecture #8
  • Lecture #9) Lab 05-2: Q-learning (Table) Demo by Jae Hyun Lee (with music)
• 팡요랩
  • Lecture #9

---

2020-02-16

• 모두를 위한 RL강좌
  • Lecture #1
  • Lecture #2
  • Lecture #3
  • Lecture #4
  • Lecture #5) Lab 3: Dummy Q-learning (table)

---

2020-02-14

• Reinforcement Learning
  • Chapter 13. Policy Gradient Methods
    • 13.5 Actor–Critic Methods
    • 13.6 Policy Gradient for Continuing Problems
    • 13.7 Policy Parameterization for Continuous Actions
    • 13.8 Summary
  • Page #339

---

2020-02-13

• Reinforcement Learning
  • Chapter 13. Policy Gradient Methods
    • 13.4 REINFORCE with Baseline
  • Page #329
• 팡요랩
  • Lecture #8

---

2020-02-11

• 팡요랩
  • Lecture #7
    • 정확하게 이해되지 않는 부분이 있어서 한 번 더 리뷰

---

2020-02-10

• 팡요랩
  • Lecture #7

---

2020-02-08

• Reinforcement Learning
  • Chapter 13. Policy Gradient Methods
    • 13.3 REINFORCE: Monte Carlo Policy Gradient
  • Page #329
• 팡요랩
  • Lecture #6

---

2020-02-05

• Reinforcement Learning
  • Chapter 13. Policy Gradient Methods
    • 13.2 The Policy Gradient Theorem
  • Page #326

---

2020-02-02

• Reinforcement Learning
  • Chapter 12. Eligibility Traces
    • 12.12 Implementation Issues
    • 12.13 Conclusions
  • Chapter 13. Policy Gradient Methods
    • 13.1 Policy Approximation and its Advantages
  • Page #324

---

Template

• Fundamental of Reinforcement Learning
  • Chapter #.
• 모두를 위한 머신러닝/딥러닝 강의
  • Lecture #.
• UCL Course on RL
  • Lecture #.
• Reinforcement Learning
  • Page #.
• 팡요랩
  • Lecture #.
• Pattern Recognition & Machine Learning