ShangtongZhang/reinforcement-learning-an-introduction

Issues

• Release date - 2nd Edition

  #7 opened 7 years ago by andrewcz
  12

• break ties in Gambler's Problem

  #83 opened 6 years ago by hansweytjens
  1

• Question about gradient in differential semi-gradient Sarsa

  #82 opened 6 years ago by HusseinAlmulla
  5

• Chapter 8: Backup updates for Prioritized Sweeping vs Dyna-Q

  #80 opened 6 years ago by xenomeno
  4

• Chapter 6: Random Walk --> Infinite loop

  #72 opened 6 years ago by xenomeno
  1

• Chapter 5: Monte Carlo ES initial policy

  #77 opened 6 years ago by jerome-white
  5

• Chapter 04: CarRental.py - suggestions for realRentalFirst/SecondLoc fix

  #81 opened 6 years ago by ychong
  2

• CHAPTER1 ,TicTacToe.py: Purpose of reshape function?

  #79 opened 6 years ago by pk97
  1

• Chapter 3: GridWorld

  #78 opened 7 years ago by ychong
  2

• chapter13

  #66 opened 7 years ago by liiiiiiiiil
  3

• Chapter4 - Suggestion

  #74 opened 7 years ago by JustinNie
  1

• One bug on the MountainCar.py in the folder Chapter12

  #71 opened 7 years ago by MathematicalModels
  1

• chapter5

  #70 opened 7 years ago by tinglo
  5

• np.argmax may lead to unexpected behavior

  #51 opened 7 years ago by ShangtongZhang
  6

• question about implementation of dealer's part in blackjack.py

  #69 opened 7 years ago by shining-spring
  1

• Policy evaluation for GridWorld

  #67 opened 7 years ago by cbrom
  4

• Possible Error in updating Gradient Bandit algorithm

  #64 opened 7 years ago by cbrom
  4

• np.random.shuffle(self.indices) in Chapter02 affects gradient

  #63 opened 7 years ago by cbrom
  2

• Chapter 4, Gambler's problem incorrect output

  #62 opened 7 years ago by sharmavedic
  2

• First-visit MC prediction for estimating v_pi

  #59 opened 7 years ago by huanghua1668
  1

• Is there any boundary for policies with off-policy Q-learning using the tree backup algorithm?

  #57 opened 7 years ago
  1

• The link to the book is broken

  #58 opened 7 years ago
  1

• One question posted on SOF

  #56 opened 7 years ago by cinqs
  1

• Make the value function invariant under rotation and mirror of the board for Tic-Tac-Toe

  #4 opened 7 years ago by ShangtongZhang
  0

• Could you please help to answer some questions?

  #49 opened 7 years ago by JieMEI1994
  2

• Shouldn't update state action value using absolute priority in Priority Sweeping

  #50 opened 7 years ago by wumo
  1

• Sarsa, Q-Learning Optimal Policy Output is Not Optimal

  #48 opened 7 years ago by mosicr
  3

• questions on Q-learning applied for racetrack

  #47 opened 7 years ago by xubo92
  1

• why 3 nested loop in function banditSimulation in TenArmedTestbed.py

  #45 opened 8 years ago by bestbzw
  1

• About the action selection in Double Q-Learning

  #46 opened 8 years ago by ewanlee
  4

• Example 4.3 Gambler's Problem Cannot Reproduce Book's Plotting

  #44 opened 8 years ago by superxingzheng
  3

• A little problem in the Gambler‘s question in chapter4

  #42 opened 8 years ago by xubo92
  8

• ImportError: No module named utils.utils

  #37 opened 8 years ago by SJTUGuofei
  7

• chapter4:Gambler question. Cannot reproduce result, why?

  #41 opened 8 years ago by xubo92
  2

• exercise 4.8

  #40 opened 8 years ago by persistforever
  2

• gambler's problem

  #39 opened 8 years ago by datahaki
  4

• Tic-Tac-Toe program didn't work well when AI is player 2.

  #36 opened 8 years ago by shengchun
  2

• should there be some changes about the code in chapter 12 "Eligibility Traces", RandomWalk.py, class "OffLineLambdaReturn" function "nStepReturnFromTime"

  #35 opened 8 years ago by xiaogengyaokeyan
  6

• Ch02 TenArmedTestbed sampleAverage

  #34 opened 8 years ago by wugh
  2

• Some explanation of tictactoe is required

  #33 opened 8 years ago by mohanr
  1

• Policy Iteration in Chapter4 for RentalCar

  #28 opened 8 years ago by loopinvariant4
  4

• debug errors for missing modules

  #27 opened 8 years ago by huiwenzhang
  1

• Maybe Error in Chapter03/GridWorld.py

  #26 opened 8 years ago by ZiJianZhao
  4

• Licensing: MIT?

  #20 opened 8 years ago by aoboturov
  1

• Confused about the implementation of figure-5-3 in Blackjack.py

  #14 opened 8 years ago by findmyway
  1

• Observation & Offer To Help

  #10 opened 8 years ago by atki4564
  1

• Ch2, line 48, 62, & 77 : don't seem to match book calc

  #9 opened 8 years ago by atki4564
  7

• Add a link to learning resource

  #2 opened 8 years ago by dmulitsa
  1

• Ch2, line 62: What does the operator '+ \' do?

  #8 opened 8 years ago by atki4564
  1