Code

Hello#241

Code

Open

simplephi wants to merge 91 commits intorevert-97-patch-1dennybritz/reinforcement-learning:revert-97-patch-1from masterdennybritz/reinforcement-learning:masterCopy head branch name to clipboard

+1,158-705

Commits

Commits on Jul 8, 2017

• Merge pull request #98 from dennybritz/revert-97-patch-1

  Show description for 67e98a9
  dennybritz

  authored
  67e98a9

  Copy full SHA for 67e98a9

• DQN copy_model_parameters memory leak fixed, tensorboard summaries updated with cpu/mem usage

  Kismuz

  committed
  71223d5

  Copy full SHA for 71223d5

Commits on Jul 9, 2017

• Merge pull request #99 from Kismuz/DQN-copy-model-params-fix

  Show description for e7085b2
  dennybritz

  authored
  e7085b2

  Copy full SHA for e7085b2

Commits on Jul 21, 2017

• Update description of env.P[s][a]

  Show description for 2b576bd
  sstarzycki

  authored
  2b576bd

  Copy full SHA for 2b576bd

• Merge pull request #102 from sstarzycki/patch-1

  Show description for 762f34c
  dennybritz

  authored
  762f34c

  Copy full SHA for 762f34c

Commits on Oct 4, 2017

• bind worker within lambda to avoid running worker twice

  himanshusahni

  committed
  1f04c1d

  Copy full SHA for 1f04c1d

• Merge pull request #111 from himanshusahni/master

  Show description for 5364539
  dennybritz

  authored
  5364539

  Copy full SHA for 5364539

Commits on Oct 10, 2017

• worker name scope should have trailing backslash otherwise any worker 10-19 will clash in scope with worker 1, and so on.

  himanshusahni

  committed
  bc7ee05

  Copy full SHA for bc7ee05

Commits on Oct 12, 2017

• Merge pull request #113 from himanshusahni/master

  Show description for 18100ea
  dennybritz

  authored
  18100ea

  Copy full SHA for 18100ea

Commits on Nov 1, 2017

• Fixed some of the issues with the DQN script as pointed out in #117

  praveen-palanisamy

  committed
  3611ec9

  Copy full SHA for 3611ec9

• Updated to support recent versions of TF. Removed deprecated functions. Pointed out in #117

  praveen-palanisamy

  committed
  e9068bf

  Copy full SHA for e9068bf

• Fixed issues with the DQN in the exercise notebook

  praveen-palanisamy

  committed
  0b2ae41

  Copy full SHA for 0b2ae41

• Fixed typo

  praveen-palanisamy

  committed
  10ce5dc

  Copy full SHA for 10ce5dc

Commits on Nov 3, 2017

• Merge pull request #118 from praveen-palanisamy/master

  Show description for 094ebf7
  dennybritz

  authored
  094ebf7

  Copy full SHA for 094ebf7

Commits on Nov 16, 2017

• Sync function descriptions. Lambda -> gamma (discount factor). Added description of env.nS and env.nA

  

  Alex

  committed
  60013e5

  Copy full SHA for 60013e5

Commits on Nov 21, 2017

• Updates function description in DP. Fixed typos in MC. Changed Lambda to Gamma as in the book.

  

  Alex

  committed
  4307667

  Copy full SHA for 4307667

Commits on Nov 22, 2017

• Fix links in all the README.mds

  Show description for 7017f9e
  jonahweissman

  committed
  7017f9e

  Copy full SHA for 7017f9e

Commits on Nov 23, 2017

• Change kernel to python3

  

  Alex

  committed
  da612e5

  Copy full SHA for da612e5

• Merge pull request #119 from BAILOOL/master

  Show description for 90b0a4a
  dennybritz

  authored
  90b0a4a

  Copy full SHA for 90b0a4a

• Merge pull request #120 from jonahweissman/master

  Show description for 7a31a2b
  dennybritz

  authored
  7a31a2b

  Copy full SHA for 7a31a2b

Commits on Nov 24, 2017

• Lambda to Gamma. Updated Readme.

  

  Alex

  committed
  79cadc0

  Copy full SHA for 79cadc0

Commits on Nov 25, 2017

• Merge pull request #121 from BAILOOL/master

  Show description for 74d301c
  dennybritz

  authored
  74d301c

  Copy full SHA for 74d301c

Commits on Dec 1, 2017

• Updated Readme. Changed Lambda to Gamma

  

  Alex

  committed
  3fce6b5

  Copy full SHA for 3fce6b5

Commits on Dec 6, 2017

• Updated link to Sutton's book

  

  Alex

  committed
  152dbc4

  Copy full SHA for 152dbc4

• Updated link to Sutton's book

  

  Alex

  committed
  9ee6cdd

  Copy full SHA for 9ee6cdd

• Merge pull request #123 from BAILOOL/master

  Show description for f45bcbf
  dennybritz

  authored
  f45bcbf

  Copy full SHA for f45bcbf

Commits on Dec 7, 2017

• DQN: Fixed typos. Changed labmda to gamma. Updated Readme

  

  Alex

  committed
  dee1e01

  Copy full SHA for dee1e01

Commits on Dec 27, 2017

• "Policy Gradient Methods" is chapter 13 now

  BAILOOL

  authored
  85565ec

  Copy full SHA for 85565ec

• "Policy Gradient Methods" chapter is completed. Updated OpenAI Gym link with cached version.

  BAILOOL

  authored
  f637c42

  Copy full SHA for f637c42

• Fixed broken links to Solutions in PolicyGradient

  BAILOOL

  authored
  1f2e2eb

  Copy full SHA for 1f2e2eb

Commits on Dec 28, 2017

• Mod. estimator_value comment in actor-critic

  

  Alex

  committed
  783c2c3

  Copy full SHA for 783c2c3

Commits on Dec 30, 2017

• Merge pull request #126 from BAILOOL/master

  Show description for 61da56c
  dennybritz

  authored
  61da56c

  Copy full SHA for 61da56c

Commits on Jan 3, 2018

• Updated links to new version of Sutton's book

  

  Alex

  committed
  d8136b4

  Copy full SHA for d8136b4

Commits on Jan 4, 2018

• Merge pull request #129 from BAILOOL/master

  Show description for fa95c7e
  dennybritz

  authored
  fa95c7e

  Copy full SHA for fa95c7e

Commits on Jan 24, 2018

• update value estimator only after calculating advantage

  keithmgould

  committed
  30326df

  Copy full SHA for 30326df

Commits on Jan 28, 2018

• Minor fix: sync sample policy with the solution

  ByzanTine

  committed
  9454010

  Copy full SHA for 9454010

Commits on Jan 29, 2018

• Merge pull request #137 from ByzanTine/master

  Show description for 2a6fe49
  dennybritz

  authored
  2a6fe49

  Copy full SHA for 2a6fe49

• Merge pull request #134 from keithmgould/master

  Show description for 5334a6f
  dennybritz

  authored
  5334a6f

  Copy full SHA for 5334a6f

Commits on Feb 19, 2018

• Add one step lookahead function for easy comparison with Value Iteration

  

  Sanyam Kapoor

  committed
  6211e2d

  Copy full SHA for 6211e2d

• Add value check assertion

  

  Sanyam Kapoor

  committed
  e030ecf

  Copy full SHA for e030ecf

• Fix step and reset NotImplementedError

  

  Sanyam Kapoor

  committed
  edcba6b

  Copy full SHA for edcba6b

• Update playground output

  

  Sanyam Kapoor

  committed
  ba12f97

  Copy full SHA for ba12f97

Commits on Feb 20, 2018

• Merge pull request #145 from activatedgeek/fix-blackjack-env

  Show description for 21a8e31
  dennybritz

  authored
  21a8e31

  Copy full SHA for 21a8e31

• Merge pull request #144 from activatedgeek/refactor-lookahead

  Show description for 5e3b1fc
  dennybritz

  authored
  5e3b1fc

  Copy full SHA for 5e3b1fc

• Fix missing render()

  

  Sanyam Kapoor

  committed
  8da669c

  Copy full SHA for 8da669c

Commits on Feb 21, 2018

• Merge pull request #146 from activatedgeek/fix-TD-envs

  Show description for 8933e3f
  dennybritz

  authored
  8933e3f

  Copy full SHA for 8933e3f

Commits on Mar 7, 2018

• Fix typo in MC Control

  Show description for 542cbf0
  jonahweissman

  authored
  542cbf0

  Copy full SHA for 542cbf0

Commits on Mar 8, 2018

• Merge pull request #148 from jonahweissman/patch-1

  Show description for 9baba87
  dennybritz

  authored
  9baba87

  Copy full SHA for 9baba87

Commits on Apr 13, 2018

• correction for state processor output shape

  ayberkydn

  committed
  c90ebaf

  Copy full SHA for c90ebaf

Commits on Apr 14, 2018

• Merge pull request #155 from aybberk/master

  Show description for e67b3cf
  dennybritz

  authored
  e67b3cf

  Copy full SHA for e67b3cf

• typo fix and correction for state processor output shape

  ayberkydn

  committed
  56f893c

  Copy full SHA for 56f893c

Commits on Apr 15, 2018

• Merge pull request #157 from aybberk/master

  Show description for 521b5a9
  dennybritz

  authored
  521b5a9

  Copy full SHA for 521b5a9

Commits on May 26, 2018

• added the equation reference

  

  Aerin Kim

  committed
  07dd722

  Copy full SHA for 07dd722

• added Sutton book's equation

  

  Aerin Kim

  committed
  377c875

  Copy full SHA for 377c875

Commits on May 27, 2018

• Merge pull request #162 from byorxyz/added_comment

  Show description for 782b951
  dennybritz

  authored
  782b951

  Copy full SHA for 782b951

Commits on May 28, 2018

• Gambler's problem (ex.4.3) added.

  

  Aerin Kim

  committed
  1b5c06f

  Copy full SHA for 1b5c06f

• Merge pull request #163 from byorxyz/ex.4.3

  Show description for 167525b
  dennybritz

  authored
  167525b

  Copy full SHA for 167525b

• just formatting

  

  Aerin Kim

  committed
  be7cfe3

  Copy full SHA for be7cfe3

• updated the broken link

  

  Aerin Kim

  committed
  4f0d942

  Copy full SHA for 4f0d942

Commits on May 29, 2018

• fix #89

  

  Aerin Kim

  committed
  fe3edfc

  Copy full SHA for fe3edfc

• Merge pull request #164 from byorxyz/ex.4.3

  Show description for dfef331
  dennybritz

  authored
  dfef331

  Copy full SHA for dfef331

Commits on Sep 20, 2018

• Update README.md

  Show description for 49631ce
  shar1pius

  authored
  49631ce

  Copy full SHA for 49631ce

Commits on Sep 21, 2018

• Merge pull request #175 from Sharwon/patch-1

  Show description for fd13eca
  dennybritz

  authored
  fd13eca

  Copy full SHA for fd13eca

Commits on Dec 24, 2018

• updates to README.md

  Show description for b47c920
  jovsa

  committed
  b47c920

  Copy full SHA for b47c920

Commits on Dec 25, 2018

• Merge pull request #187 from JovanSardinha/master

  Show description for 8e8a21b
  dennybritz

  authored
  8e8a21b

  Copy full SHA for 8e8a21b

• imported io so that StringIO() would work

  jovsa

  committed
  57f71cd

  Copy full SHA for 57f71cd

• added documentation for _render()

  jovsa

  committed
  9ad2689

  Copy full SHA for 9ad2689

• documented structure for P[s][a]

  jovsa

  committed
  0fe550c

  Copy full SHA for 0fe550c

• removed extra whitespace

  jovsa

  committed
  30b2304

  Copy full SHA for 30b2304

• nit

  jovsa

  committed
  01b8b13

  Copy full SHA for 01b8b13

Commits on Dec 26, 2018

• Merge pull request #188 from JovanSardinha/master

  Show description for cee9e78
  dennybritz

  authored
  cee9e78

  Copy full SHA for cee9e78

Commits on Feb 27, 2019

• Add link to Advanced Depp Learning & Reinforcement Learning lectures on youtube.

  Show description for 120fbcf
  

  Stas Olekhnovich

  committed
  120fbcf

  Copy full SHA for 120fbcf

Commits on Mar 1, 2019

• fixed shape descriptions for neural network input layer

  alek5k

  committed
  4a2df43

  Copy full SHA for 4a2df43

Commits on Mar 2, 2019

• Merge pull request #194 from alek5k/dqn-fixes

  Show description for e4797f2
  dennybritz

  authored
  e4797f2

  Copy full SHA for e4797f2

• Merge pull request #193 from fspirit/add_deepmind_course_link

  Show description for 706b13a
  dennybritz

  authored
  706b13a

  Copy full SHA for 706b13a

Commits on Mar 13, 2019

• Updated links to new version of Sutton's book

  PieroMacaluso

  committed
  a35df15

  Copy full SHA for a35df15

• Merge pull request #195 from pieromacaluso/master

  Show description for b7b4d3d
  dennybritz

  authored
  b7b4d3d

  Copy full SHA for b7b4d3d

Commits on Mar 29, 2019

• Fix rendering crash on Win 10

  Show description for bb9241d
  fspirit

  authored
  bb9241d

  Copy full SHA for bb9241d

Commits on Apr 2, 2019

• Q-Learning docstring improvements.

  anuzis

  committed
  1abaae4

  Copy full SHA for 1abaae4

Commits on Apr 3, 2019

• Merge pull request #199 from anuzis/master

  Show description for 59cded5
  dennybritz

  authored
  59cded5

  Copy full SHA for 59cded5

Commits on Jun 11, 2019

• Update CliffWalk REINFORCE with Baseline Solution.ipynb

  guotong1988

  authored
  b2d179a

  Copy full SHA for b2d179a

Commits on Jun 24, 2019

• Merge pull request #201 from guotong1988/patch-1

  Show description for 9dce017
  dennybritz

  authored
  9dce017

  Copy full SHA for 9dce017

• Merge pull request #198 from fspirit/fix-rendering-crash-on-win-10

  Show description for 92205f5
  dennybritz

  authored
  92205f5

  Copy full SHA for 92205f5

Commits on Oct 1, 2019

• Update Policy Iteration Solution.ipynb

  quanturk

  authored
  775fd81

  Copy full SHA for 775fd81

• Update Policy Iteration Solution.ipynb

  quanturk

  authored
  7d23260

  Copy full SHA for 7d23260

Commits on Oct 2, 2019

• Merge pull request #214 from nsydn/master

  Show description for 89dacf5
  dennybritz

  authored
  89dacf5

  Copy full SHA for 89dacf5

Commits on Nov 8, 2019

• Update README.md

  roshray

  authored
  1298c8d

  Copy full SHA for 1298c8d

Commits on Nov 9, 2019

• Merge pull request #216 from roshray/patch-1

  Show description for 06ce312
  dennybritz

  authored
  06ce312

  Copy full SHA for 06ce312

Commits on Sep 19, 2022

• Compatible with gym==0.26

  arielsboiardi

  committed
  40eda6b

  Copy full SHA for 40eda6b

Commits on Sep 20, 2022

• Corrected import

  arielsboiardi

  committed
  d173521

  Copy full SHA for d173521

• Merge pull request #245 from arielsboiardi/master

  Show description for 2b83228
  dennybritz

  authored
  2b83228

  Copy full SHA for 2b83228