├── Assignments ├── hw1fall2017.pdf ├── hw2_final.pdf ├── hw3_final.pdf └── hw4_final.pdf ├── Hopper_Backflips.gif ├── LICENSE ├── Lectures ├── guest_lecture_advanced_model_learning.pdf ├── lecture_10_imitating_optimal_control.pdf ├── lecture_11_control_and_inference.pdf ├── lecture_12_inverse_reinforcement_learning.pdf ├── lecture_13_advanced_pg.pdf ├── lecture_13_exploration.pdf ├── lecture_14_transfer.pdf ├── lecture_15_multi_task_learning.pdf ├── lecture_16_meta_learning.pdf ├── lecture_17_challenges.pdf ├── lecture_1_introduction.pdf ├── lecture_2_behavior_cloning.pdf ├── lecture_3_rl_intro.pdf ├── lecture_4_policy_gradient.pdf ├── lecture_5_actor_critic_pdf.pdf ├── lecture_6_value_functions.pdf ├── lecture_7_advanced_q_learning.pdf ├── lecture_8_model_based_planning.pdf ├── lecture_9_model_based_rl.pdf └── tf_review_session.pdf ├── README.md ├── hw1 ├── README.md ├── dagger.py ├── demo.bash ├── experts │ ├── Ant-v1.pkl │ ├── HalfCheetah-v1.pkl │ ├── Hopper-v1.pkl │ ├── Humanoid-v1.pkl │ ├── Reacher-v1.pkl │ └── Walker2d-v1.pkl ├── load_policy.py ├── load_policy.pyc ├── plotting.py ├── run_cloning.py ├── run_expert.py ├── tf_util.py └── tf_util.pyc ├── hw2 ├── README.md ├── fig │ ├── 1_cartpole_sb.png │ ├── 2_cartpole_lb.png │ ├── 2_cartpole_sb_lb.png │ ├── 3_pendulum_2x16.png │ ├── 4_nn_baseline.png │ └── 5_hc.png ├── logz.py ├── plot.py └── train_pg.py ├── hw3 ├── README ├── atari_wrappers.py ├── dqn.py ├── dqn_utils.py ├── run_dqn_atari.py └── run_dqn_ram.py └── hw4 ├── README.md ├── cheetah_env.py ├── controllers.py ├── cost_functions.py ├── dynamics.py ├── logz.py ├── main.py └── plot.py /Assignments/hw1fall2017.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Assignments/hw1fall2017.pdf -------------------------------------------------------------------------------- /Assignments/hw2_final.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Assignments/hw2_final.pdf -------------------------------------------------------------------------------- /Assignments/hw3_final.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Assignments/hw3_final.pdf -------------------------------------------------------------------------------- /Assignments/hw4_final.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Assignments/hw4_final.pdf -------------------------------------------------------------------------------- /Hopper_Backflips.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Hopper_Backflips.gif -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/LICENSE -------------------------------------------------------------------------------- /Lectures/guest_lecture_advanced_model_learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/guest_lecture_advanced_model_learning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_10_imitating_optimal_control.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_10_imitating_optimal_control.pdf -------------------------------------------------------------------------------- /Lectures/lecture_11_control_and_inference.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_11_control_and_inference.pdf -------------------------------------------------------------------------------- /Lectures/lecture_12_inverse_reinforcement_learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_12_inverse_reinforcement_learning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_13_advanced_pg.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_13_advanced_pg.pdf -------------------------------------------------------------------------------- /Lectures/lecture_13_exploration.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_13_exploration.pdf -------------------------------------------------------------------------------- /Lectures/lecture_14_transfer.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_14_transfer.pdf -------------------------------------------------------------------------------- /Lectures/lecture_15_multi_task_learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_15_multi_task_learning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_16_meta_learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_16_meta_learning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_17_challenges.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_17_challenges.pdf -------------------------------------------------------------------------------- /Lectures/lecture_1_introduction.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_1_introduction.pdf -------------------------------------------------------------------------------- /Lectures/lecture_2_behavior_cloning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_2_behavior_cloning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_3_rl_intro.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_3_rl_intro.pdf -------------------------------------------------------------------------------- /Lectures/lecture_4_policy_gradient.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_4_policy_gradient.pdf -------------------------------------------------------------------------------- /Lectures/lecture_5_actor_critic_pdf.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_5_actor_critic_pdf.pdf -------------------------------------------------------------------------------- /Lectures/lecture_6_value_functions.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_6_value_functions.pdf -------------------------------------------------------------------------------- /Lectures/lecture_7_advanced_q_learning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_7_advanced_q_learning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_8_model_based_planning.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_8_model_based_planning.pdf -------------------------------------------------------------------------------- /Lectures/lecture_9_model_based_rl.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/lecture_9_model_based_rl.pdf -------------------------------------------------------------------------------- /Lectures/tf_review_session.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/Lectures/tf_review_session.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/README.md -------------------------------------------------------------------------------- /hw1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/README.md -------------------------------------------------------------------------------- /hw1/dagger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/dagger.py -------------------------------------------------------------------------------- /hw1/demo.bash: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/demo.bash -------------------------------------------------------------------------------- /hw1/experts/Ant-v1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/experts/Ant-v1.pkl -------------------------------------------------------------------------------- /hw1/experts/HalfCheetah-v1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/experts/HalfCheetah-v1.pkl -------------------------------------------------------------------------------- /hw1/experts/Hopper-v1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/experts/Hopper-v1.pkl -------------------------------------------------------------------------------- /hw1/experts/Humanoid-v1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/experts/Humanoid-v1.pkl -------------------------------------------------------------------------------- /hw1/experts/Reacher-v1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/experts/Reacher-v1.pkl -------------------------------------------------------------------------------- /hw1/experts/Walker2d-v1.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/experts/Walker2d-v1.pkl -------------------------------------------------------------------------------- /hw1/load_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/load_policy.py -------------------------------------------------------------------------------- /hw1/load_policy.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/load_policy.pyc -------------------------------------------------------------------------------- /hw1/plotting.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/plotting.py -------------------------------------------------------------------------------- /hw1/run_cloning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/run_cloning.py -------------------------------------------------------------------------------- /hw1/run_expert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/run_expert.py -------------------------------------------------------------------------------- /hw1/tf_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/tf_util.py -------------------------------------------------------------------------------- /hw1/tf_util.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw1/tf_util.pyc -------------------------------------------------------------------------------- /hw2/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/README.md -------------------------------------------------------------------------------- /hw2/fig/1_cartpole_sb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/fig/1_cartpole_sb.png -------------------------------------------------------------------------------- /hw2/fig/2_cartpole_lb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/fig/2_cartpole_lb.png -------------------------------------------------------------------------------- /hw2/fig/2_cartpole_sb_lb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/fig/2_cartpole_sb_lb.png -------------------------------------------------------------------------------- /hw2/fig/3_pendulum_2x16.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/fig/3_pendulum_2x16.png -------------------------------------------------------------------------------- /hw2/fig/4_nn_baseline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/fig/4_nn_baseline.png -------------------------------------------------------------------------------- /hw2/fig/5_hc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/fig/5_hc.png -------------------------------------------------------------------------------- /hw2/logz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/logz.py -------------------------------------------------------------------------------- /hw2/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/plot.py -------------------------------------------------------------------------------- /hw2/train_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw2/train_pg.py -------------------------------------------------------------------------------- /hw3/README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw3/README -------------------------------------------------------------------------------- /hw3/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw3/atari_wrappers.py -------------------------------------------------------------------------------- /hw3/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw3/dqn.py -------------------------------------------------------------------------------- /hw3/dqn_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw3/dqn_utils.py -------------------------------------------------------------------------------- /hw3/run_dqn_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw3/run_dqn_atari.py -------------------------------------------------------------------------------- /hw3/run_dqn_ram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw3/run_dqn_ram.py -------------------------------------------------------------------------------- /hw4/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/README.md -------------------------------------------------------------------------------- /hw4/cheetah_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/cheetah_env.py -------------------------------------------------------------------------------- /hw4/controllers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/controllers.py -------------------------------------------------------------------------------- /hw4/cost_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/cost_functions.py -------------------------------------------------------------------------------- /hw4/dynamics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/dynamics.py -------------------------------------------------------------------------------- /hw4/logz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/logz.py -------------------------------------------------------------------------------- /hw4/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/main.py -------------------------------------------------------------------------------- /hw4/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/khanhnamle1994/deep-reinforcement-learning/HEAD/hw4/plot.py --------------------------------------------------------------------------------