├── README.md ├── codes ├── basic.ipynb ├── bayesian.ipynb ├── cartpole_a2c.ipynb ├── cartpole_dqn.ipynb ├── cartpole_ppo.ipynb ├── cartpole_ppo_bayesian.ipynb ├── cartpole_ppo_bayesian_test.ipynb ├── cartpole_ppo_gridsearch.ipynb ├── cartpole_ppo_gridsearch_test.ipynb ├── cartpole_ppo_tuned.ipynb ├── cartpole_reinforce.ipynb ├── cartpole_run.ipynb ├── env.ipynb ├── model │ ├── a2c │ │ ├── saved_model.pb │ │ └── variables │ │ │ ├── variables.data-00000-of-00001 │ │ │ └── variables.index │ ├── dqn │ │ ├── saved_model.pb │ │ └── variables │ │ │ ├── variables.data-00000-of-00001 │ │ │ └── variables.index │ ├── ppo │ │ ├── saved_model.pb │ │ └── variables │ │ │ ├── variables.data-00000-of-00001 │ │ │ └── variables.index │ ├── ppo_tunned │ │ ├── saved_model.pb │ │ └── variables │ │ │ ├── variables.data-00000-of-00001 │ │ │ └── variables.index │ └── reinforce │ │ ├── saved_model.pb │ │ └── variables │ │ ├── variables.data-00000-of-00001 │ │ └── variables.index └── test.ipynb ├── notes ├── 01.1.강의소개.pdf ├── 02.1.강화학습 개념-확률과정.pdf ├── 02.2.강화학습 개념-마르코프 연쇄.pdf ├── 02.3.강화학습 개념-마르코프 보상과정.pdf ├── 03.1.강화학습 기본 알고리즘-마르코프 결정과정.pdf ├── 03.2.강화학습 기본 알고리즘-다이나믹 프로그래밍.pdf ├── 03.3.강화학습 기본 알고리즘-몬테카를로 방법.pdf ├── 03.4.강화학습 기본 알고리즘-TD와 SARSA.pdf ├── 03.5.강화학습 기본 알고리즘-Q러닝.pdf └── hello.txt └── 오류조치-2022년12월10일 /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/README.md -------------------------------------------------------------------------------- /codes/basic.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/basic.ipynb -------------------------------------------------------------------------------- /codes/bayesian.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/bayesian.ipynb -------------------------------------------------------------------------------- /codes/cartpole_a2c.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_a2c.ipynb -------------------------------------------------------------------------------- /codes/cartpole_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_dqn.ipynb -------------------------------------------------------------------------------- /codes/cartpole_ppo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_ppo.ipynb -------------------------------------------------------------------------------- /codes/cartpole_ppo_bayesian.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_ppo_bayesian.ipynb -------------------------------------------------------------------------------- /codes/cartpole_ppo_bayesian_test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_ppo_bayesian_test.ipynb -------------------------------------------------------------------------------- /codes/cartpole_ppo_gridsearch.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_ppo_gridsearch.ipynb -------------------------------------------------------------------------------- /codes/cartpole_ppo_gridsearch_test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_ppo_gridsearch_test.ipynb -------------------------------------------------------------------------------- /codes/cartpole_ppo_tuned.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_ppo_tuned.ipynb -------------------------------------------------------------------------------- /codes/cartpole_reinforce.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_reinforce.ipynb -------------------------------------------------------------------------------- /codes/cartpole_run.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/cartpole_run.ipynb -------------------------------------------------------------------------------- /codes/env.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/env.ipynb -------------------------------------------------------------------------------- /codes/model/a2c/saved_model.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/a2c/saved_model.pb -------------------------------------------------------------------------------- /codes/model/a2c/variables/variables.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/a2c/variables/variables.data-00000-of-00001 -------------------------------------------------------------------------------- /codes/model/a2c/variables/variables.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/a2c/variables/variables.index -------------------------------------------------------------------------------- /codes/model/dqn/saved_model.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/dqn/saved_model.pb -------------------------------------------------------------------------------- /codes/model/dqn/variables/variables.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/dqn/variables/variables.data-00000-of-00001 -------------------------------------------------------------------------------- /codes/model/dqn/variables/variables.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/dqn/variables/variables.index -------------------------------------------------------------------------------- /codes/model/ppo/saved_model.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/ppo/saved_model.pb -------------------------------------------------------------------------------- /codes/model/ppo/variables/variables.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/ppo/variables/variables.data-00000-of-00001 -------------------------------------------------------------------------------- /codes/model/ppo/variables/variables.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/ppo/variables/variables.index -------------------------------------------------------------------------------- /codes/model/ppo_tunned/saved_model.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/ppo_tunned/saved_model.pb -------------------------------------------------------------------------------- /codes/model/ppo_tunned/variables/variables.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/ppo_tunned/variables/variables.data-00000-of-00001 -------------------------------------------------------------------------------- /codes/model/ppo_tunned/variables/variables.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/ppo_tunned/variables/variables.index -------------------------------------------------------------------------------- /codes/model/reinforce/saved_model.pb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/reinforce/saved_model.pb -------------------------------------------------------------------------------- /codes/model/reinforce/variables/variables.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/reinforce/variables/variables.data-00000-of-00001 -------------------------------------------------------------------------------- /codes/model/reinforce/variables/variables.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/model/reinforce/variables/variables.index -------------------------------------------------------------------------------- /codes/test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/codes/test.ipynb -------------------------------------------------------------------------------- /notes/01.1.강의소개.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/01.1.강의소개.pdf -------------------------------------------------------------------------------- /notes/02.1.강화학습 개념-확률과정.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/02.1.강화학습 개념-확률과정.pdf -------------------------------------------------------------------------------- /notes/02.2.강화학습 개념-마르코프 연쇄.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/02.2.강화학습 개념-마르코프 연쇄.pdf -------------------------------------------------------------------------------- /notes/02.3.강화학습 개념-마르코프 보상과정.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/02.3.강화학습 개념-마르코프 보상과정.pdf -------------------------------------------------------------------------------- /notes/03.1.강화학습 기본 알고리즘-마르코프 결정과정.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/03.1.강화학습 기본 알고리즘-마르코프 결정과정.pdf -------------------------------------------------------------------------------- /notes/03.2.강화학습 기본 알고리즘-다이나믹 프로그래밍.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/03.2.강화학습 기본 알고리즘-다이나믹 프로그래밍.pdf -------------------------------------------------------------------------------- /notes/03.3.강화학습 기본 알고리즘-몬테카를로 방법.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/03.3.강화학습 기본 알고리즘-몬테카를로 방법.pdf -------------------------------------------------------------------------------- /notes/03.4.강화학습 기본 알고리즘-TD와 SARSA.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/03.4.강화학습 기본 알고리즘-TD와 SARSA.pdf -------------------------------------------------------------------------------- /notes/03.5.강화학습 기본 알고리즘-Q러닝.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/notes/03.5.강화학습 기본 알고리즘-Q러닝.pdf -------------------------------------------------------------------------------- /notes/hello.txt: -------------------------------------------------------------------------------- 1 | ddd 2 | -------------------------------------------------------------------------------- /오류조치-2022년12월10일: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/multicore-it/rl/HEAD/오류조치-2022년12월10일 --------------------------------------------------------------------------------