├── README.md ├── week1_intro ├── crossentropy_method.ipynb ├── deep_crossentropy_method.ipynb ├── gym_interface.ipynb ├── pong.py ├── primer │ ├── recap_ml.ipynb │ ├── recap_tensorflow.ipynb │ └── train.csv ├── project_starter_evolution_strategies.ipynb └── submit.py ├── week2_model_based ├── mdp.py ├── practice_vi.ipynb └── submit.py ├── week3_model_free ├── experience_replay.ipynb ├── qlearning.ipynb ├── qlearning.py ├── sarsa.ipynb └── submit.py ├── week4_approx ├── atari_util.py ├── dqn_atari.ipynb ├── framebuffer.py ├── img │ ├── 1.png │ ├── 2.png │ ├── cnn.png │ ├── exp_rep.png │ └── target.png ├── practice_approx_qlearning.ipynb ├── replay_buffer.py └── submit.py ├── week5_policy_based ├── atari_util.py ├── img │ ├── nnet_arch.png │ ├── parallel.png │ └── train.gif ├── practice_a3c.ipynb ├── practice_reinforce.ipynb └── submit.py └── week6_outro ├── bandits.ipynb ├── practice_mcts.ipynb ├── seq2seq ├── basic_model_tf.py ├── he-pron-wiktionary.txt ├── main_dataset.txt ├── practice_tf.ipynb └── voc.py └── submit.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/README.md -------------------------------------------------------------------------------- /week1_intro/crossentropy_method.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/crossentropy_method.ipynb -------------------------------------------------------------------------------- /week1_intro/deep_crossentropy_method.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/deep_crossentropy_method.ipynb -------------------------------------------------------------------------------- /week1_intro/gym_interface.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/gym_interface.ipynb -------------------------------------------------------------------------------- /week1_intro/pong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/pong.py -------------------------------------------------------------------------------- /week1_intro/primer/recap_ml.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/primer/recap_ml.ipynb -------------------------------------------------------------------------------- /week1_intro/primer/recap_tensorflow.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/primer/recap_tensorflow.ipynb -------------------------------------------------------------------------------- /week1_intro/primer/train.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/primer/train.csv -------------------------------------------------------------------------------- /week1_intro/project_starter_evolution_strategies.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/project_starter_evolution_strategies.ipynb -------------------------------------------------------------------------------- /week1_intro/submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week1_intro/submit.py -------------------------------------------------------------------------------- /week2_model_based/mdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week2_model_based/mdp.py -------------------------------------------------------------------------------- /week2_model_based/practice_vi.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week2_model_based/practice_vi.ipynb -------------------------------------------------------------------------------- /week2_model_based/submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week2_model_based/submit.py -------------------------------------------------------------------------------- /week3_model_free/experience_replay.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week3_model_free/experience_replay.ipynb -------------------------------------------------------------------------------- /week3_model_free/qlearning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week3_model_free/qlearning.ipynb -------------------------------------------------------------------------------- /week3_model_free/qlearning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week3_model_free/qlearning.py -------------------------------------------------------------------------------- /week3_model_free/sarsa.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week3_model_free/sarsa.ipynb -------------------------------------------------------------------------------- /week3_model_free/submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week3_model_free/submit.py -------------------------------------------------------------------------------- /week4_approx/atari_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/atari_util.py -------------------------------------------------------------------------------- /week4_approx/dqn_atari.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/dqn_atari.ipynb -------------------------------------------------------------------------------- /week4_approx/framebuffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/framebuffer.py -------------------------------------------------------------------------------- /week4_approx/img/1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/img/1.png -------------------------------------------------------------------------------- /week4_approx/img/2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/img/2.png -------------------------------------------------------------------------------- /week4_approx/img/cnn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/img/cnn.png -------------------------------------------------------------------------------- /week4_approx/img/exp_rep.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/img/exp_rep.png -------------------------------------------------------------------------------- /week4_approx/img/target.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/img/target.png -------------------------------------------------------------------------------- /week4_approx/practice_approx_qlearning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/practice_approx_qlearning.ipynb -------------------------------------------------------------------------------- /week4_approx/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/replay_buffer.py -------------------------------------------------------------------------------- /week4_approx/submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week4_approx/submit.py -------------------------------------------------------------------------------- /week5_policy_based/atari_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/atari_util.py -------------------------------------------------------------------------------- /week5_policy_based/img/nnet_arch.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/img/nnet_arch.png -------------------------------------------------------------------------------- /week5_policy_based/img/parallel.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/img/parallel.png -------------------------------------------------------------------------------- /week5_policy_based/img/train.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/img/train.gif -------------------------------------------------------------------------------- /week5_policy_based/practice_a3c.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/practice_a3c.ipynb -------------------------------------------------------------------------------- /week5_policy_based/practice_reinforce.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/practice_reinforce.ipynb -------------------------------------------------------------------------------- /week5_policy_based/submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week5_policy_based/submit.py -------------------------------------------------------------------------------- /week6_outro/bandits.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/bandits.ipynb -------------------------------------------------------------------------------- /week6_outro/practice_mcts.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/practice_mcts.ipynb -------------------------------------------------------------------------------- /week6_outro/seq2seq/basic_model_tf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/seq2seq/basic_model_tf.py -------------------------------------------------------------------------------- /week6_outro/seq2seq/he-pron-wiktionary.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/seq2seq/he-pron-wiktionary.txt -------------------------------------------------------------------------------- /week6_outro/seq2seq/main_dataset.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/seq2seq/main_dataset.txt -------------------------------------------------------------------------------- /week6_outro/seq2seq/practice_tf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/seq2seq/practice_tf.ipynb -------------------------------------------------------------------------------- /week6_outro/seq2seq/voc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/seq2seq/voc.py -------------------------------------------------------------------------------- /week6_outro/submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/b13302/Practical_RL-coursera/HEAD/week6_outro/submit.py --------------------------------------------------------------------------------