Ecosyste.ms: OpenCollective

An open API service for software projects hosted on Open Collective.

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl

A reinforcement learning package for Julia
https://github.com/JuliaReinforcementLearning/ReinforcementLearning.jl

refactor existing components (#26)

d6b6186c38148843c3ad42993ecd2e6afb69dbf2 authored over 5 years ago by Jun Tian <[email protected]>
update Hanabi.jl (#12)

* update Hanabi.jl

* support Julia 1.0

* update README.md

0bf89ba14f8e37e739baa8a336838bc5a04b8750 authored over 5 years ago by Jun Tian <[email protected]>
add DiscreteMazeEnv (#10)

7b9c802a1aaa3ec1ff1ba4b04fb37f1d0a503c3b authored over 5 years ago by jbrea <[email protected]>
ignore ViZDoom error for now (#11)

* allow ViZDoom broken

* bugfix

* ignore ViZDoom for now

* add some quick fixes, mdp.jl...

899a197210bb1820c18f81df1873127078fd8e7b authored over 5 years ago by Jun Tian <[email protected]>
Add ContinuousMountainCar (#8)

* Int64 -> Int

* add continuous mountain car

c3bc6c53aeff604b1a45e7ac89b57a682b255d7a authored over 5 years ago by jbrea <[email protected]>
Merge pull request #7 from JuliaReinforcementLearning/jb/simplemdp

add more flexible reward schemes to SimpleMDPEnv

4f4db44a61e7865dc518403b3c3af77f469973c4 authored over 5 years ago by jbrea <[email protected]>
add more flexible reward schemes to SimpleMDPEnv

f1eb43cdd8a13d6dcf782f05d2a0a7786f315c67 authored over 5 years ago by Johanni Brea <[email protected]>
test atari envs but defender

b6a5222fdf36dcebbe1feea4afcd751b060947b5 authored over 5 years ago by Johanni Brea <[email protected]>
adapt to new ALE version

e914d266c2cabccf447b98a2835d0f3803f7687f authored over 5 years ago by Johanni Brea <[email protected]>
get screen width and height

06472c7e0d00719c9285a512dbeef04750da9775 authored over 5 years ago by jbrea <[email protected]>
add more useful functions for Hanabi

3d78c3b70c4830570e0e1650f6c83649ee33424e authored almost 6 years ago by Jun Tian <[email protected]>
bugfix in Hanabi (#6)

* bugfix

88491a497f7153ef933f0fc7f4e192a4af77baf9 authored almost 6 years ago by Jun Tian <[email protected]>
Update Hanabi (#5)

* pre-allocate all moves

a8a432248c1208b8ac58c0bb02669a57a71c038f authored almost 6 years ago by Jun Tian <[email protected]>
Add Benchmarks (#4)

* testing...

* update

* update benchmarks

3a632e26804fdfb21cbafee3a64672026ebcdc32 authored almost 6 years ago by Jun Tian <[email protected]>
update uuid of Hanabi.jl

4924be8dc9363a199aa2a73771b2f8b6e6e2a56b authored almost 6 years ago by Jun Tian <[email protected]>
Add Hanabi (#3)

* add HanabiEnv

a7c4d9ab8eb9162f58aab1f369d7beedeb6255e9 authored almost 6 years ago by Jun Tian <[email protected]>
Merge pull request #2 from JuliaReinforcementLearning/gym

Support OpenAI Gym Environments

f650f45c758ed2235af2ba2061da2e3745cece35 authored almost 6 years ago by Jun Tian <[email protected]>
bugfix

86fd98f654f89f2a0b0c9af4f56f30bcf517e992 authored almost 6 years ago by Jun Tian <[email protected]>
bugfix

5fac87e49cd993bc8fc00fe8775c34fcf00157fb authored almost 6 years ago by Jun Tian <[email protected]>
update readme

4a2985ad911b62452a49d3081a182e0a5af6fcd9 authored almost 6 years ago by Jun Tian <[email protected]>
bug fix

4a0f8eaee45ab79e5da5c2b6fb9bfa5dce3b1584 authored almost 6 years ago by Jun Tian <[email protected]>
fix name issue

59eb7facf2f878ca721d2804d022c823be3e199b authored almost 6 years ago by Jun Tian <[email protected]>
support gym

80b00c18b393b3a367c5d1874a37d4eb494a88ea authored almost 6 years ago by Jun Tian <[email protected]>
merge master

50e66717e42fcaaa65e40b0e6b4e9083ba6c5be5 authored almost 6 years ago by Jun Tian <[email protected]>
add TupleSpace and DictSpace

aadafe8c0fa394af0448b05d2fe8e0f8c0542872 authored almost 6 years ago by Jun Tian <[email protected]>
add extra spaces

26475ec73d9aec0d7910d42bf58881a6d2b6cbb9 authored almost 6 years ago by Jun Tian <[email protected]>
Add Hanabi

0ffc3b8031cce686590371567db790135a123f3a authored almost 6 years ago by Jun Tian <[email protected]>
Merge pull request #1 from JuliaReinforcementLearning/jun/vizdoom

Support ViZDoom

d20ebb2c00c7a041a2818bdde9dbdc9448353280 authored almost 6 years ago by Jun Tian <[email protected]>
remove coverage temporary

0a7847b5d1d8d6e1fc3f9a4891545699e29f0388 authored almost 6 years ago by Jun Tian <[email protected]>
typo fix

aec5fc10a277192a44779efb5c1bad273e6127b0 authored almost 6 years ago by Jun Tian <[email protected]>
use docker to test

a4050a4a216726d069ae56004bb73b88fa138a0b authored almost 6 years ago by Jun Tian <[email protected]>
support ViZDoom

3c4dad590bd441af85a2e529735fab6ff58cd59c authored almost 6 years ago by Jun Tian <[email protected]>
add todo

890031c1d9caad8aa9f2ce697e8087982e3f8791 authored almost 6 years ago by Jun Tian <[email protected]>
remove redundant code

2a7cdf5dce4e12b67452b47eddce39c254f5bedf authored almost 6 years ago by Jun Tian <[email protected]>
remove redundant code

a497d71b43b548da29d98db9d7d5310505ff20bb authored almost 6 years ago by Jun Tian <[email protected]>
add badges

7de55fdb83d75eb8efdc18f74cb8e32df484502a authored almost 6 years ago by Jun Tian <[email protected]>
update README.md

116d8699baf08508f204bb6496294c715ecc9447 authored almost 6 years ago by Jun Tian <[email protected]>
add travis

f47e9a7af554aeb265114c77661de71a44df62b4 authored almost 6 years ago by Jun Tian <[email protected]>
init

c3d62c8c2bbb156fca6f9c215753f8e88973641a authored almost 6 years ago by Jun Tian <[email protected]>
minor change

f57c88bfe9897c66e51f63d8a37f5ad7b8767baf authored almost 6 years ago by Jun Tian <[email protected]>
test

03e9fd77e09a8f99dd4e409ec68d8bc46909d69c authored almost 6 years ago by Jun Tian <[email protected]>
test

0a4cb57e6f83d1a2028df22af7ef3f2adc8715aa authored almost 6 years ago by Jun Tian <[email protected]>
test

477703fc850580628c72ef6920f72e3044f53931 authored almost 6 years ago by Jun Tian <[email protected]>
add classic control environments

e83ee79c6310f3d26a5cba5952797f3cc48a0134 authored almost 6 years ago by Jun Tian <[email protected]>
temp

51fc9349b447f6d91097fb6cfcbef0ed48433dd2 authored almost 6 years ago by Jun Tian <[email protected]>
temp

3c2492e7bd69a2d556e3d9156c3f77311b8d0e59 authored almost 6 years ago by Jun Tian <[email protected]>
generalize samplegreedyaction

58fdbef14546db8d49562709830b531e58a403ea authored almost 6 years ago by Johanni Brea <[email protected]>
fix EvaluateGreedy

3f06a7b537efb75710d6083a824a91bb7fddfdd7 authored about 6 years ago by Johanni Brea <[email protected]>
adapt tutorial

d726c289c4821eed71b46201b4e372649e00fa88 authored over 6 years ago by Johanni Brea <[email protected]>
Update README.md

fdbdbbc59d30ce5795ebfe8157cce5ec035e0343 authored over 6 years ago by jbrea <[email protected]>
Merge pull request #18 from JuliaReinforcementLearning/fix_examples

fix examples

2126960d4d394b77d47d7c2ade7a1bcc983a849b authored over 6 years ago by jbrea <[email protected]>
fix forced policy

5342d7c55efe0a6755cb448d150070c4c0ece1d4 authored over 6 years ago by Johanni Brea <[email protected]>
update benchmarks

ef63d1c70cc43dcc6b9a2011b206473e990bddba authored over 6 years ago by Johanni Brea <[email protected]>
adding some benchmark files

184a59490f5eadc2bbc61368fa2fe1c92cd3bc33 authored over 6 years ago by Johanni Brea <[email protected]>
improve docs

535ae54c5f17363f3324b87cd4b028bea047d867 authored over 6 years ago by Johanni Brea <[email protected]>
deploy docs on julia 1.0

b27d7b21e06fec60cc38e1522c985ddb99abcd16 authored over 6 years ago by Johanni Brea <[email protected]>
fix travis after_success

2845c051b0e27cf68a3d25130ce859feaced4626 authored over 6 years ago by Johanni Brea <[email protected]>
fix env loading in docs

59e7be27c86d3c9b62606e4addb951afc911079d authored over 6 years ago by Johanni Brea <[email protected]>
fix examples

0beba5f640734dd1656e7bdd883648da26105456 authored over 6 years ago by Johanni Brea <[email protected]>
export functions

cb11ba7680a075c322f3a2690d55fab505881c3f authored over 6 years ago by Johanni Brea <[email protected]>
Merge pull request #4 from JuliaReinforcementLearning/test_envinterface

import relevant methods

17a7d78eb0657d9ad0fb70b26091810d9876664b authored over 6 years ago by jbrea <[email protected]>
import relevant methods

55a5153ae8c04f36adaf8bc62aa86000bd96af2c authored over 6 years ago by Johanni Brea <[email protected]>
Merge pull request #3 from JuliaReinforcementLearning/test_envinterface

add test_envinterface

ce77348d2e6580ffcdb402ca327de63eef2b10f8 authored over 6 years ago by Jun Tian <[email protected]>
add test_envinterface

ebfd690911a077d0b9099ebf6008b57a91b49c2f authored over 6 years ago by Johanni Brea <[email protected]>
Merge pull request #15 from JuliaReinforcementLearning/refactor_policy

refactor policies

d7edebeb4f0f17151b47b9dd9bf4cc5d11568fd7 authored over 6 years ago by jbrea <[email protected]>
fix tests

77891859ef48d3eef7acec2f73b0bf1db581a4bf authored over 6 years ago by Johanni Brea <[email protected]>
import sample from base

f1188a880c3ea5b8bc6eac5d0b3495b1a684c9e6 authored over 6 years ago by jbrea <[email protected]>
sample from actionspace

3576604dcb2dfc5ef715eb21df83fe70cc99edf5 authored over 6 years ago by jbrea <[email protected]>
defaultpolicy should depend on actionspace

2f46bc03b7eff852a3f97997900ab5fea09286fa authored over 6 years ago by jbrea <[email protected]>
Merge branch 'master' into refactor_policy

a7a03d4da74c5b91b8c67af8f10b754ec7da5819 authored over 6 years ago by jbrea <[email protected]>
Merge pull request #16 from JuliaReinforcementLearning/rlbase

Add ReinforcementLearningBase as dependent

d03ee2854bc8f07873ce9dcd58b445dcf4b1ffc1 authored over 6 years ago by jbrea <[email protected]>
fix plotenv

32c40ff971aa751e728ad4453fe6dc7ff51d6ac0 authored over 6 years ago by Johanni Brea <[email protected]>
Add ReinforcementLearningBase as dependent; test move MDP to Discrete; drop pre 1.0 support

bab0ddeea99796c835e8c1dd66f2980c423ecfd5 authored over 6 years ago by Johanni Brea <[email protected]>
use StatsBase.wsample

53320be2e8a8124cd968542b4d039a170b54ffa0 authored over 6 years ago by Johanni Brea <[email protected]>
fix getnmarkov

b33948caf525675efc4d1e8fbb11a56f0681b8e0 authored over 6 years ago by Johanni Brea <[email protected]>
refactor policies

c84f78ea8f7a705b49f3ac5d36350073d0f839bc authored over 6 years ago by Johanni Brea <[email protected]>
Merge pull request #1 from findmyway/master

Add Space & AbstractEnv into base

937076c70633bced57129c87fded3abcc7b85403 authored over 6 years ago by jbrea <[email protected]>
add REQUIRE

fb4a9e3c7c434a8a424585c78041f199ef52afca authored over 6 years ago by Jun Tian <[email protected]>
Resolve Comments

e7c5b1c3b094e56033088087362e49ac51d83a10 authored over 6 years ago by Jun Tian <[email protected]>
add .travis

302c42dd03c571b1a37d72db981891cc2e3c3e4c authored over 6 years ago by Jun Tian <[email protected]>
rename

9c6afe74d9c125ca1168ccb688280c418e47d729 authored over 6 years ago by Jun Tian <[email protected]>
init

41eb43e96de6009c3a21ebb920a160edbcc23498 authored over 6 years ago by Jun Tian <[email protected]>
initial commit

8249aa390a7c3d3ab5069766e3f634091abd9f1e authored over 6 years ago by Johanni Brea <[email protected]>
rename environments

f295820e6ab12bde03f3e4ce2a7a38dbb021eb97 authored over 6 years ago by Johanni Brea <[email protected]>
Merge pull request #13 from JuliaReinforcementLearning/improve_doc

improve docs

24578f3c9048fd84f2580df443a9117b199c21e5 authored over 6 years ago by jbrea <[email protected]>
Merge pull request #12 from JuliaReinforcementLearning/refactor_epsgreedy

implement epsilon-greedy policy with parametric type

e435e20f0a6ac7ffb82aaf1697a8ddd75116188c authored over 6 years ago by jbrea <[email protected]>
improve docs

efe3668040fca627b0698c01133146c09a439d30 authored over 6 years ago by Johanni Brea <[email protected]>
implement epsilon-greedy policy with parametric type

5b59a70de3968403a1c0d50e724f369fac4a04fa authored over 6 years ago by Johanni Brea <[email protected]>
test julia 1.0

da6c597fd2a34d1ee8e69b3ababe2745b6e9b5d8 authored over 6 years ago by jbrea <[email protected]>
add doc

353c06791fde01d02beb1b2a69c9d57cc8c3f7c5 authored over 6 years ago by Johanni Brea <[email protected]>
simplify

bb74043c17aafa7dc51934fa7bad4c84be27d735 authored over 6 years ago by Johanni Brea <[email protected]>
update docs

8f035d65696ddab9f37cb69959259f10454440f0 authored over 6 years ago by Johanni Brea <[email protected]>
adapt docs

4b28b3821b5160600a9e8c0bfe1bc2e2245f3955 authored over 6 years ago by Johanni Brea <[email protected]>
update urls; installation description

e9c4eb3c298bf4a9d3577c34dfae491de7b1076c authored over 6 years ago by Johanni Brea <[email protected]>
fix v0.6

faafa8bacbe667cf80f743df972668321329c90c authored over 6 years ago by Johanni Brea <[email protected]>
allow sorted dict

3cc4be2f0f21301f6662023b639eb1c3c142b62d authored over 6 years ago by Johanni Brea <[email protected]>
don't run q-network when random action is selected

69773b2aec28435ed30b76bbee05120b926c256d authored over 6 years ago by Johanni Brea <[email protected]>
fix test errors

9a5f1d72e1cb2442eabee2d26df240aee24f3de9 authored over 6 years ago by Johanni Brea <[email protected]>
add nstep qlearning

e5b9445d0b14256ed8a310c0407cd4799b528b83 authored over 6 years ago by root <[email protected]>
use setindex for performance

599ae9a06ad16b4d272d690b7b3b2f24ab79b7f5 authored over 6 years ago by root <[email protected]>