deep-reinforcement-learning:加州大学伯克利分校CS 294的编程作业和讲座
需积分: 10 138 浏览量
2021-05-01
09:20:53
上传
评论
收藏 80.54MB ZIP 举报
deep-reinforcement-learning-master.zip （67个子文件） 
deep-reinforcement-learning-master Lectures 
lecture_1_introduction.pdf 3.41MB guest_lecture_advanced_model_learning.pdf 28.46MB lecture_3_rl_intro.pdf 2.17MB lecture_12_inverse_reinforcement_learning.pdf 3.82MB lecture_16_meta_learning.pdf 2.58MB lecture_14_transfer.pdf 3.6MB lecture_13_exploration.pdf 2.87MB lecture_9_model_based_rl.pdf 3.75MB lecture_17_challenges.pdf 3.22MB lecture_8_model_based_planning.pdf 2.72MB lecture_2_behavior_cloning.pdf 2.36MB lecture_10_imitating_optimal_control.pdf 3.21MB lecture_6_value_functions.pdf 2.14MB lecture_13_advanced_pg.pdf 847KB lecture_7_advanced_q_learning.pdf 2.6MB tf_review_session.pdf 239KB lecture_4_policy_gradient.pdf 2.44MB lecture_5_actor_critic_pdf.pdf 2.35MB lecture_15_multi_task_learning.pdf 2.95MB lecture_11_control_and_inference.pdf 2.52MB
LICENSE 1KB hw3 atari_wrappers.py 5KB run_dqn_ram.py 4KB dqn.py 15KB run_dqn_atari.py 4KB README 196B dqn_utils.py 13KB README.md 7KB hw2 fig 
2_cartpole_lb.png 144KB 5_hc.png 81KB 4_nn_baseline.png 194KB 2_cartpole_sb_lb.png 150KB 1_cartpole_sb.png 190KB 3_pendulum_2x16.png 122KB logz.py 3KB README.md 6KB train_pg.py 23KB plot.py 3KB hw1 run_cloning.py 4KB dagger.py 5KB tf_util.py 17KB experts Reacher-v1.pkl 63KB Hopper-v1.pkl 64KB Humanoid-v1.pkl 367KB HalfCheetah-v1.pkl 71KB Ant-v1.pkl 148KB Walker2d-v1.pkl 71KB demo.bash 174B load_policy.py 2KB load_policy.pyc 3KB README.md 719B plotting.py 2KB tf_util.pyc 24KB run_expert.py 2KB Assignments hw1fall2017.pdf 94KB hw4_final.pdf 164KB hw2_final.pdf 149KB hw3_final.pdf 96KB hw4 controllers.py 1KB logz.py 3KB main.py 11KB cheetah_env.py 1KB README.md 3KB cost_functions.py 2KB dynamics.py 4KB plot.py 3KB
Hopper_Backflips.gif 4.68MB
评论0