Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / ShangtongZhang/reinforcement-learning-an-introduction issues and pull requests

#166 - A different implementation for car rental problem

Pull Request - State: open - Opened by kevinnewgame about 2 months ago

#164 - Update car_rental.py to use np.int32 instead of np.int

Pull Request - State: open - Opened by wvul 3 months ago - 1 comment

#163 - Add CITATION.cff

Pull Request - State: open - Opened by RensOliemans over 1 year ago - 4 comments

#162 - Citing this repository

Issue - State: open - Opened by RensOliemans over 1 year ago

#160 - (fix): ten_armed_testbed.py np.float

Pull Request - State: closed - Opened by iw4p over 1 year ago

#159 - Fixed START, GOAL state

Pull Request - State: open - Opened by MichaelQiYinChen over 1 year ago

#157 - ch06 random_walk td method

Issue - State: open - Opened by Perseus1993 almost 2 years ago - 1 comment

#156 - l

Issue - State: open - Opened by Karp8841 about 2 years ago

#155 - Unclear point for the code in Blackjack example

Issue - State: open - Opened by eatam almost 3 years ago - 1 comment

#154 - Wrong Bellman equation for Jack's car rental problem?

Issue - State: closed - Opened by Raymondliz almost 3 years ago - 1 comment

#153 - The plicy of chapter1

Issue - State: open - Opened by benroo123 almost 3 years ago - 1 comment

#152 - Problem of excercise 2.5

Issue - State: open - Opened by qiqiJiang-st almost 3 years ago

#151 - example to use it on human genetic data?

Issue - State: open - Opened by Shicheng-Guo about 3 years ago

#150 - problem about chapter04/car_rental.py

Issue - State: open - Opened by shaoeChen about 3 years ago - 1 comment

#148 - Minor changes

Pull Request - State: closed - Opened by VEXLife over 3 years ago - 1 comment

#147 - wrong figure number for chapter 11

Issue - State: open - Opened by arashHaratian over 3 years ago

#146 - typo

Issue - State: closed - Opened by arashHaratian over 3 years ago

#145 - tictactoe compete() plays 1000 almost identical games

Issue - State: open - Opened by gsverhoeven over 3 years ago - 1 comment

#144 - add script that reproduces example 12.14

Pull Request - State: closed - Opened by Johann-Huber over 3 years ago - 1 comment

#143 - Figure 5.3 change

Pull Request - State: closed - Opened by VEXLife over 3 years ago - 2 comments

#142 - Change the axis limit and offset.

Pull Request - State: closed - Opened by VEXLife over 3 years ago - 1 comment

#141 - Generalization to abstract classes for Environment/Agents?

Issue - State: closed - Opened by chicotobi over 3 years ago - 2 comments

#140 - Patch 1

Pull Request - State: closed - Opened by VEXLife over 3 years ago - 2 comments

#139 - something wrong in matplotlib

Issue - State: open - Opened by FYYFU almost 4 years ago - 2 comments

#138 - Update trajectory_sampling.py

Pull Request - State: closed - Opened by vinnik-dmitry07 almost 4 years ago

#137 - docs: fix simple typo, resoultion -> resolution

Pull Request - State: closed - Opened by timgates42 almost 4 years ago - 1 comment

#136 - nit: chapter 6 references

Issue - State: open - Opened by mahiuchun almost 4 years ago

#135 - A simpler draw function

Issue - State: open - Opened by rohitdavas about 4 years ago - 2 comments

#134 - Unable to get the same results while formulating differently

Issue - State: closed - Opened by rohitdavas about 4 years ago - 1 comment

#133 - No related package on the zip file

Issue - State: closed - Opened by leiyongxiang1205 about 4 years ago - 1 comment

#132 - add state labels on the tables

Pull Request - State: closed - Opened by yasutak over 4 years ago - 1 comment

#131 - reinforcement-learning

Pull Request - State: closed - Opened by yang-chenyu104 over 4 years ago

#130 - Add code to draw optimal policy

Pull Request - State: closed - Opened by rogertrullo over 4 years ago - 1 comment

#129 - Add linear system to gridworld

Pull Request - State: closed - Opened by rogertrullo over 4 years ago - 1 comment

#128 - Help on ten_armed_testbed.py

Issue - State: closed - Opened by ai4pharma over 4 years ago - 3 comments

#127 - Chapter4, gambler problem

Issue - State: closed - Opened by 07hyx06 over 4 years ago - 1 comment

#126 - Chapter 11

Issue - State: closed - Opened by mattgithub1919 over 4 years ago - 12 comments

#125 - chap1/tic_tac_toc.py why does make td_error zero when exploring

Issue - State: closed - Opened by GarfieldF over 4 years ago - 1 comment

#124 - chapter04/car_rental_synchronous.py: the table needs to be flipped.

Issue - State: closed - Opened by QuangTran4810 about 5 years ago - 1 comment

#123 - chapter06/random_wark.py

Issue - State: closed - Opened by ChenHuaYou about 5 years ago - 1 comment

#122 - a little confuse about chapter5/blackjack.py

Issue - State: closed - Opened by ChenHuaYou about 5 years ago - 2 comments

#121 - chapter04/gamblers_problem.py line33 to 62 may has a problem

Issue - State: closed - Opened by ChenHuaYou about 5 years ago - 2 comments

#120 - Reinforcement learning

Issue - State: closed - Opened by palbha about 5 years ago - 1 comment

#119 - Update figures 13_1 and 13_2

Pull Request - State: closed - Opened by scrpy about 5 years ago - 1 comment

#118 - discount factor for Chapter 10

Issue - State: closed - Opened by roachsinai about 5 years ago - 1 comment

#117 - Misunderstanding in chapter 2

Issue - State: closed - Opened by zZthebreakerZz over 5 years ago - 1 comment

#116 - Tile Coding scaling issue

Issue - State: closed - Opened by MJeremy2017 over 5 years ago - 2 comments

#115 - Fix usable_ace_player bug, fix indention error, set POLICY_PLAYER dty…

Pull Request - State: closed - Opened by goal over 5 years ago - 1 comment

#114 - How to formulate problem with State is a combination of multiple factors?

Issue - State: closed - Opened by MJeremy2017 over 5 years ago - 1 comment

#113 - Chapter 4：seems missing self. before TRUNCATE

Issue - State: closed - Opened by ZiqiChai over 5 years ago - 1 comment

#112 - Chapter 2: reset time

Issue - State: closed - Opened by sursu over 5 years ago - 2 comments

#111 - Pythonic edits

Pull Request - State: closed - Opened by billtubbs over 5 years ago - 1 comment

#110 - Choosing the best action when identical

Pull Request - State: closed - Opened by sursu over 5 years ago

#109 - modification for chap04

Pull Request - State: closed - Opened by wlbksy over 5 years ago - 1 comment

#108 - simplify update equations respect to the book

Pull Request - State: closed - Opened by wlbksy over 5 years ago - 1 comment

#107 - pythonic for chap01

Pull Request - State: closed - Opened by wlbksy over 5 years ago - 1 comment

#106 - Fixed few minor issues in chapter 1 tic_tac_toe:

Pull Request - State: closed - Opened by ainilaha over 5 years ago - 1 comment

#105 - Fixed epsilon value for exploration

Pull Request - State: closed - Opened by abhinavsagar over 5 years ago - 2 comments

#104 - epilon not initialized

Issue - State: closed - Opened by abhinavsagar over 5 years ago - 1 comment

#103 - Maybe a little bug in chapter5 blackjack.py function 'play' line 81-85

Issue - State: closed - Opened by Huixxi over 5 years ago - 1 comment

#102 - Policy evaluation with backed up value function.

Pull Request - State: closed - Opened by tahsinkose over 5 years ago - 1 comment

#101 - Chapter 09: Random Walk 100

Issue - State: closed - Opened by xenomeno almost 6 years ago - 1 comment

#100 - Question about batch_updating function in chapter06/random_walk.py

Issue - State: closed - Opened by hitblackjack almost 6 years ago - 1 comment

#98 - Missing parameter description for true_reward

Issue - State: closed - Opened by michaelshiyu almost 6 years ago - 2 comments

#97 - Made the epsilon-greedy bandit algorithm break ties at random.

Pull Request - State: closed - Opened by michaelshiyu almost 6 years ago - 2 comments

#96 - Just a Thank you note

Issue - State: closed - Opened by wassimseif almost 6 years ago

#95 - Chapter01 - Fix lint messages, add parameter to reduce frequency of logging

Pull Request - State: closed - Opened by VVKot almost 6 years ago - 1 comment

#94 - Why do not use true online Sarsa(λ) in figure 12.11

Issue - State: closed - Opened by xingE650 almost 6 years ago - 1 comment

#93 - Chapter 4 jacks car rental

Issue - State: closed - Opened by HareshKarnan almost 6 years ago - 2 comments

#92 - _

Issue - State: closed - Opened by hitblackjack almost 6 years ago - 1 comment

#91 - Problem I meet in how TD method and MC method update the last state-value in a MRP

Issue - State: closed - Opened by xingE650 almost 6 years ago - 1 comment

#89 - chapter2_content.tex exercise 2.3 问题

Issue - State: closed - Opened by RocStone about 6 years ago - 1 comment

#88 - action index should offset by one

Pull Request - State: closed - Opened by barcahead about 6 years ago - 1 comment

#87 - Some revision suggestions in Maximization_bias's Problem

Pull Request - State: closed - Opened by LBAWMY about 6 years ago - 1 comment

#86 - Some revision suggestions in Maximization_bias's Problem

Issue - State: closed - Opened by LBAWMY about 6 years ago - 1 comment

#85 - Add docker files to configure runtime eonvironment

Pull Request - State: closed - Opened by YangyangFu about 6 years ago - 2 comments

#84 - Q-learning Example Has No @expected

Issue - State: closed - Opened by LinaeSostra about 6 years ago - 1 comment

#83 - break ties in Gambler's Problem

Issue - State: closed - Opened by hansweytjens about 6 years ago - 1 comment

#82 - Question about gradient in differential semi-gradient Sarsa

Issue - State: closed - Opened by HusseinAlmulla about 6 years ago - 5 comments

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

Issue - State: closed - Opened by ychong over 6 years ago - 2 comments

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

Issue - State: closed - Opened by xenomeno over 6 years ago - 4 comments

#79 - CHAPTER1 ,TicTacToe.py: Purpose of reshape function?

Issue - State: closed - Opened by pk97 over 6 years ago - 1 comment

#78 - Chapter 3: GridWorld

Issue - State: closed - Opened by ychong over 6 years ago - 2 comments

#77 - Chapter 5: Monte Carlo ES initial policy

Issue - State: closed - Opened by jerome-white over 6 years ago - 5 comments

#76 - Chapter 13, REINFORCE

Pull Request - State: closed - Opened by sergii-bond over 6 years ago - 1 comment

#75 - Add in place version of Chapter 4

Pull Request - State: closed - Opened by JustinNie over 6 years ago - 1 comment

#74 - Chapter4 - Suggestion

Issue - State: closed - Opened by JustinNie over 6 years ago - 1 comment

#73 - add example 13.1

Pull Request - State: closed - Opened by sergii-bond over 6 years ago - 1 comment

#72 - Chapter 6: Random Walk --> Infinite loop

Issue - State: closed - Opened by xenomeno over 6 years ago - 1 comment

#71 - One bug on the MountainCar.py in the folder Chapter12

Issue - State: closed - Opened by MathematicalModels over 6 years ago - 1 comment

#70 - chapter5

Issue - State: closed - Opened by tinglo over 6 years ago - 5 comments

#69 - question about implementation of dealer's part in blackjack.py

Issue - State: closed - Opened by shining-spring over 6 years ago - 1 comment

#68 - Policy evaluation for GridWorld issue #67

Pull Request - State: closed - Opened by cbrom over 6 years ago

#67 - Policy evaluation for GridWorld

Issue - State: closed - Opened by cbrom over 6 years ago - 4 comments