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
* fix #48
* fix typo
a0d659cde7c67138a15a8553c26a0d9a769d743d authored over 4 years ago by Jun Tian <[email protected]>350f940f8267bedf1029d52c3b143d5fe1b43e70 authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
5b794ddd40c9ada144f0b2aab7f412253fad9ee5 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* add RandomStartPolicy
* rename TupleSpace to VectSpace for efficiency
9bdbbce5f996aab58033f10a345a0da9cf6833f8 authored over 4 years ago by Jun Tian <[email protected]>* add summary for StateCachedEnv
* remove unnecessary summary
caaa23f6ca60940c0b3e253693ad8ca50b691dd0 authored over 4 years ago by Jun Tian <[email protected]>0271a4f4397b0164732f040d5c3d2a9f0acac7c7 authored over 4 years ago by Jun Tian <[email protected]>
afc0c8cbaba819d4e1db34d716a7e2e826d5a73b authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
d3bd122e16080c1bee799e658cfd6a08d36a5a69 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>ff92907f1a2cc618cce8e220778182b48f3a2a43 authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
660aa2808ae21a096b7b24475ab63db5bdf77e52 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
abc1c4aa0f89102d976ca8194a19d20d1205230d authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>1a17d2e2ee3e1f3fa69f160d98664f7f38acf8d0 authored over 4 years ago by noreply <[email protected]>
* sync
* simplify methods in RLBase
* add default description of env
* remove Observati...
2ea7d6cdcca67ed75a27e8f7662a89fcfd558c28 authored over 4 years ago by Jun Tian <[email protected]>3c9deae4027089682fe9afa2401770d87c483bc7 authored over 4 years ago by noreply <[email protected]>
08fa98a37c486cddcee27fdfddc9e04dcc3368cb authored over 4 years ago by Jun Tian <[email protected]>
0ad441263875683c0c4f54c1dcd3dad497073fd5 authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
db54bd6e0c4b3dac319cfc84734ae59d94a48dec authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* resolve performance issue when calculating loss
* decrease number of params in JuliRL_DDPG_...
f0a2692cba66de31158c664be0f446252b858b1f authored over 4 years ago by Jun Tian <[email protected]>6b60c3d2af3b02ba420b76844e62b081cbc5e02c authored over 4 years ago by Felix Chalumeau <[email protected]>
1ca67b558d66e2f4823f7df8e6144924662c7e5f authored over 4 years ago by noreply <[email protected]>
8b3073f58ae6facd1b37a4365285858c59a913fc authored over 4 years ago by Jun Tian <[email protected]>
* allow setting maximum frames in atari env
* clip reward in Atari experiments
348db84aec3925900829e78617ce7ff51a9538cd authored over 4 years ago by Jun Tian <[email protected]>de6ac8ebe3619261df6f8d95543d608e04920064 authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
9c74d45ae480b6d06b61f2455754dacd19ebe3fc authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>5d12cdb48c9a3ed057fa8691c274894149d4a7b3 authored over 4 years ago by Jun Tian <[email protected]>
aa5cd3d260ab076fa3697197f5b95ddeab6f2390 authored over 4 years ago by Jun Tian <[email protected]>
b83fe0d7c225b9a885df1cbba4cba8449bd5325e authored over 4 years ago by Jun Tian <[email protected]>
9b75221f1227d8145c488fa4250d3cd6103a5941 authored over 4 years ago by Jun Tian <[email protected]>
8b8988be94d6706a17d69551a7f6ed0cdd6e67d3 authored over 4 years ago by Jun Tian <[email protected]>
bc58eb692f6aa33ef9108fe926892ccf35c42860 authored over 4 years ago by Jun Tian <[email protected]>
7398c303a28882a772742c6c3774cf65cb5342bb authored over 4 years ago by Jun Tian <[email protected]>
15ad9ab045dda62a59604e7711877b1a37ed3278 authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
0a4a190638eac35f203ba44a33370c9918ae94f3 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* fix bug in sum tree
* sampling trick =。=
0ad52d3c082f4ec093166f0143c6925c71aa6b2f authored over 4 years ago by Jun Tian <[email protected]>51700db0839236774d6b32ba59028a1cd10ebb16 authored over 4 years ago by jbrea <[email protected]>
61d76dbc4d91ae7f9c1cf65b272289bbf3c83d89 authored over 4 years ago by noreply <[email protected]>
c91eeebb2748344fb85fa321d3c7ff1f8d5f785d authored over 4 years ago by Jun Tian <[email protected]>
913fcb6d8e91e940b2500132135be9a11968e541 authored over 4 years ago by Jun Tian <[email protected]>
67de4eb07b92c427a7c3fb72189a6b688ec634aa authored over 4 years ago by noreply <[email protected]>
9e11c2e8dcd69bba6756b4c7d3ce809cedf0c797 authored over 4 years ago by Jun Tian <[email protected]>
aa93cb5df526b69f02113dad94e921d2a0bb4897 authored over 4 years ago by Jun Tian <[email protected]>
23f4336670c311c83d39f5e9561e15047d2736c2 authored over 4 years ago by Jun Tian <[email protected]>
53907cbffcaa0432812f57376f1d38e42a4731fd authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
ec36851290f43693fc268244c926b70c83c65466 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>4d6998fce71546db9e6d6c6fc6b3554cf13fb78a authored over 4 years ago by Jun Tian <[email protected]>
268e26cd1527f94bf5036bcf7ce888a1b8756f6d authored over 4 years ago by Jun Tian <[email protected]>
5b8411d9cde5b6f655339c6a3286056688530f7d authored over 4 years ago by Jun Tian <[email protected]>
cad7f2765f0d83be78faab3809b8903248833eda authored over 4 years ago by Jun Tian <[email protected]>
* add documentation stage in travis
* fix image links
* reorder contents
* update doc t...
2a998fc4c3d55f3f11d1a9e9f47e7e4331e12765 authored over 4 years ago by Jun Tian <[email protected]>bc7e08a83c6af032e3925e5a98709dc9c463db0c authored over 4 years ago by Jun Tian <[email protected]>
0efbf65b2f4d067051de54923bc4456870d0f671 authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
ee613a5a87ec05a78e3590fee685e90f633bc1a9 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>7de43e831a0f18141706e8fcb275774307fd7087 authored over 4 years ago by Jun Tian <[email protected]>
df5b7b8fbeec7bfebc23328eca3a5bc5b88fef42 authored over 4 years ago by Jun Tian <[email protected]>
705356d1787918f94a5fc6244637747fe80471f7 authored over 4 years ago by Jun Tian <[email protected]>
6f6ea18adc3c39f94b5712b62736d9e63479fb2e authored over 4 years ago by noreply <[email protected]>
f27e5c5e10d7ca8a3af63af819838b7abf831dfc authored over 4 years ago by Jun Tian <[email protected]>
aec0ce6705cf8644ba8f41877ad0d97ae046c919 authored over 4 years ago by noreply <[email protected]>
* CompatHelper: bump compat for "Adapt" to "2.0"
* Update Project.toml
Co-authored-by: git...
d1bd5301ab3a6a956576c2bbd119a1675ba79c9e authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>78dbcdae8882348b6d0662c6863476a9e0b1d65c authored over 4 years ago by jbrea <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
c5602b9f020e0a88c7109bb1e7b771e8fb3e4e95 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* fix render
* parametric action
* import OrdinaryDiffEq
* fixes #27
* Array -> Abst...
e4108dde274d8461362b5c8e4808a5a18a83a48a authored over 4 years ago by jbrea <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
a2f55ba12bfcc7b1e946d57e628495ad12565f57 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>d4e481500b1ab7c9ecb0ee7c0b262304a34cabcf authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
ff90b0852da3b732ce68c343bbaf82f5d7517a7c authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
4ed0ff54565214e31b5cd244da4becf0c17a7779 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
a928d7fc32c8d9d0c5e1a4a354ff93cb28d7c7e9 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>da986792180355ee5da682038b9d2a242b5863d1 authored over 4 years ago by Jun Tian <[email protected]>
* add PPO
* revert changes
* add an experiment of PPO on CartPole
* add ppo
* add PP...
384054269bec69f26eb21584241f43ed7f0462a5 authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
81f682bf53de376e7c98ad66b84cfe919a25defa authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
49677b729d89f980983908051ab481ec421a00ee authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>331482af8587ad391d47d13ba7878836ee199324 authored over 4 years ago by Jun Tian <[email protected]>
* Add discrete, fix angle_normalize and reset! in Pendulum
* set actions and rename _interact...
19a721865eca9d3940b30af87d2e0ac4e1238ca4 authored over 4 years ago by Alex Lewandowski <[email protected]>* add ddpg
* export DDPGPolicy
* add experiment for DDPG
* remove unused test file
*...
7375b9d1b7ae01613ab04f78bde86870ac17862d authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
67eaeb2e10972505d878908c1974076a69a5cbff authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>ref https://github.com/JuliaReinforcementLearning/ReinforcementLearningCore.jl/issues/76
20593a406d599a2bafb6efef2150f035ad5b679a authored over 4 years ago by Jun Tian <[email protected]>* bugfix with A2C
* add experiment for A2CGAE
* only update A2CGAE in Training mode
8bc5f234ce453c14cb31693375ad7ada07a388c4 authored over 4 years ago by Jun Tian <[email protected]>6251e3c0c8cd5e09af327b621f9ebbe42337614c authored over 4 years ago by Jun Tian <[email protected]>
35517b40431385d7eeea53defc5e9001df5522e5 authored over 4 years ago by Johanni Brea <[email protected]>
9dabf6446d8751134b2907db6c602053b242fe44 authored over 4 years ago by Johanni Brea <[email protected]>
2104d7b2fbd1870b667504623ba9098b76120a9c authored over 4 years ago by Johanni Brea <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
134b7ba83c4fc4ad343d0d49e84a8aaa868a9cca authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
6bad15dc9f73fc94d007160e1c2236ac93f6f41f authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>b7af0005395c30499e37b7b6f944bec5805a68e3 authored over 4 years ago by Jun Tian <[email protected]>
* export Training Testing
* let the user decide calling gpu or not
* uncomment the huber_l...
72443d81a5ffad7ca62579bdc1d3ade69f96ef55 authored over 4 years ago by Jun Tian <[email protected]>214114145156e7fa9281c956da11c5ee7076e9f4 authored over 4 years ago by Jun Tian <[email protected]>
543bfd2e165aa77f5b375ac8725970967f982168 authored over 4 years ago by noreply <[email protected]>
fef8a5920e78aff2eb40599bee00df8b28a1bbbd authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
d62db2b33ee52e2361f4fb1cba721e45e3486470 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* CompatHelper: add new compat entry for "OrdinaryDiffEq" at version "5.39"
* Update Project....
4c93f364f67707928dfbfec363f589be9601854b authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>added acrobot code
423c19588a2099be4501a8bcce6c702b63ba3202 authored over 4 years ago by jbrea <[email protected]>a1a3a5138316495a73985b3f5890779e0537bcff authored over 4 years ago by Pavan BG <[email protected]>
a1b236f8a436727edf218a40ac0c494056eaf3fa authored over 4 years ago by Pavan BG <[email protected]>
b430acb01d888129a8960588e965e5b42d5edb86 authored over 4 years ago by Pavan BG <[email protected]>
4dbdcd5ddb22427340204a22c1d6ef9c24949cb3 authored over 4 years ago by Pavan BG <[email protected]>
80ca7c1d9a376c95abdbd2ef7884981891ebd73d authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
6ad001bdc72295fb3d07aaa4cfd731e6150ea218 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>c708fca7d70ec58f4c3562451fc03bef9a54850c authored over 4 years ago by Jun Tian <[email protected]>
* add IQN
* uncomment tests
* fix method missing error
* add atari experiment for iqn &...
8483e50048c1be5c85b45c009008f3094dd8d1e5 authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
84a193da73b670545fb595a963febed7819f67c0 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>