01 Chapter 0 ģ¤ė¦¬ģķ
ģ“ģ
RL ģģ
ģź° (Introduction)
ģ§ė¬øķźø°
ģ¶ź° ģė£
ģ¶ź° ģė£ź° ģģµėė¤
ģ¬źø°ģ ģė”ģ“ ķģµ ģė£ė„¼ ķģøķģøģ!
ģ ģėģ“ ģ¶ź°ķ ģė£ė¤ģ ė°ė” ķģøķ ģ ģģ“ģ.
ėŖØėė„¼ ģķ ė„ė¬ė - Deep Reinforcement Learning
- 01Chapter 0 ģ¤ė¦¬ģķ ģ“ģ
- 02Chapter 1 OpenAI GYM ź²ģķ“ė³“źø°
- 03Chapter 2 Dummy Q-learning (table)
- 04Chapter 3 Q-learning explit&exploration and discounted reward
- 05Chapter 4 Q-learning in non-deterministic world
- 06Chapter 5 Q-Network
- 07Chapter 6 DQN
RL ģģ
ģź° (Introduction)
[ģ“ė” ] Playing OpenAI GYM Games
[ģ¤ģµ] Playing OpenAI GYM Games
[ģ“ė” ] Dummy Q-learning (table)
[ģ¤ģµ] Dummy Q-learning (table)
[ģ“ė” ] Q-learning exploit&exploration and discounted reward
[ģ¤ģµ] Q-learning exploit&exploration and discounted reward
[ģ“ė” ] Q-learning in non-deterministic world
[ģ¤ģµ] Q-learning in non-deterministic world
[ģ¤ģµ] Q-learning(Table) Demo by Jae Hyun Lee
[ģ“ė” ] Q-Network
[ģ¤ģµ] Q-Network for Frozen Lake
[ģ¤ģµ] Q-Network for Cart Pole
[ģ“ė” ] DQN
[ģ¤ģµ] DQN 1 (NIPS 2013)
[ģ¤ģµ] DQN 2 (Nature 2015)
[ģ¤ģµ] DQN Cart Pole Demo (with Music!)
[ģ¤ģµ] DQN Simple Pacman Demo (ģ¬ė¬ė¶ģ ģµź³ ėŖģ ź¹ģ§ ź°ģ ģėģ?)
RL ģģ
ģź° (Introduction)