reinforcement_learning_specialisation_notes:强化学习专家的笔记
需积分: 7 16 浏览量
2021-03-19
14:20:01
上传
评论
收藏 118.92MB ZIP 举报
reinforcement_learning_specialisation_notes:强化学习专家的笔记 （220个子文件） 
C2M2-Assignment-v4-submitted.ipynb 829KB Assignment1-v2.ipynb 665KB Assignment1-v2.ipynb 665KB assignment.ipynb 604KB C2M2-Assignment-v4.ipynb 416KB C2M2-Assignment-v4-submitted-v2.ipynb 278KB assignment.ipynb 184KB C1M4_Assignment2-v3.ipynb 178KB Blackjack.ipynb 50KB
ch3-exercises.jpg 190KB wk1.md 27KB wk3.md 20KB wk1.md 19KB wk4.md 15KB wk2.md 13KB wk4.md 12KB wk3.md 11KB wk2.md 10KB README.md 1KB textbook-reading-todo.md 1KB TODO.md 337B step_size.npy 1.53MB step_size.npy 1.53MB e-greedy_scores.npy 1.53MB e-greedy_scores.npy 1.53MB expected_sarsa.npy 391KB q_learning.npy 391KB greedy_scores.npy 8KB greedy_scores.npy 8KB optimal_policy_value_fn.npy 512B e-greedy_test.npy 168B e-greedy-0.01.npy 168B greedy_test.npy 168B e-greedy-1.0.npy 168B e-greedy-0.5.npy 168B e-greedy-0.1.npy 168B e-greedy_test.npy 168B e-greedy-0.01.npy 168B greedy_test.npy 168B e-greedy-1.0.npy 168B e-greedy-0.5.npy 168B e-greedy-0.1.npy 168B argmax_test.npy 160B argmax_test.npy 160B
Course_01_Notes_Santiago_Zubieta.pdf 8.75MB Sample-Based-Learning-Methods-Learning-Objectives.pdf 83KB Fundamentals-of-Reinforcement-Learning_Learning-Objectives.pdf 65KB RLbook2020trimmed.pdf 71.64MB
wk5-quiz-answers.png 2.49MB wk1-quiz.png 2.21MB wk2-quiz.png 1.76MB wk3-Richard-Sutton.png 1.59MB wk3-quiz.png 1.44MB wk3-quiz.png 1.29MB wk2-quiz.png 1.22MB wk4-quiz.png 1.18MB wk1-quiz.png 934KB wk3-quiz-prac.png 814KB wk2-monte-carlo-off-policy-v-pi-algorithm.png 723KB wk2-epsilon-soft-pseudocode.png 666KB wk4-quiz.png 552KB wk3-gridworld-state-all-eq.png 481KB wk4-value-iteration-algorithm.png 469KB wk5-planning-steps-vs-learning.png 452KB wk5-quadratic-approximation-steps.png 450KB wk3-RMS-error-TD-vs-MC.png 437KB wk5-quadratic-approximation-formula.png 423KB wk4-revisiting-bellman-equations.png 421KB wk4-policy-improvement-formulae.png 417KB wk3-choosing-argmax-a.png 415KB wk4-dynamic-programming-uses-p.png 413KB wk1-epsilon-greedy-10-armed-01.png 411KB wk4-subtleties-with-off-policy-control.png 406KB wk2-episodic-vs-continuing.png 403KB wk3-summary-03.png 402KB wk1-contextual-bandits-real-world.png 401KB wk2-effect of-gamma.png 397KB wk4-sarsa-vs-Q-episode-rewards.png 377KB wk3-bellman-optimality-solving.png 366KB wk2-monte-carlo-GPI-01.png 364KB wk3-state-value-bellman-eq.png 362KB wk4-gridworld-converged.png 362KB wk2-off-policy-trajectories.png 360KB wk4-expected-sarsa-off-policy.png 356KB wk4-iterative-policy-evaluation-pseudocode.png 354KB wk5-quadratic-approximation-resources.png 353KB wk4-windy-gridworld-parameter-study.png 352KB wk2-continuing-discounting.png 350KB wk4-sarsa-windy-gridworld.png 348KB wk2-action-values-and-exploration.png 345KB wk4-expected-vs-sarsa-parameter-study-50000x.png 341KB wk4-gridworld-01.png 340KB wk4-TD-control-agorithm-comparison.png 339KB wk3-gridworld-state-A-eq.png 338KB wk5-random-sample-one-step-tabular-Q-learning.png 337KB wk3-bellman-optimality-v-star.png 336KB wk3-determining-optimal-policy-diagram.png 335KB wk2-continuing-finality.png 330KB wk2-blakjack-state-values-01.png 328KB wk3-optimal-policy-example.png 327KB共 220 条
- 1
- 2
- 3
评论0