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
55c2037f0d9f9d475ee0cc7286b7a3a1961502f0 authored over 4 years ago by Jun Tian <[email protected]>
* add reservoir_array_buffer
* bugfix with ReservoirArrayBuffer
* minor improvement
* m...
bd916e5b00d33624be29db0aba4c0c0cb3fecf00 authored over 4 years ago by Jun Tian <[email protected]>* add GPU differentiable logpdf for normal distributions
* add tests on GPU
Co-authored-by...
d022f549eb2fa2cfb9678afedd34d21b89f4974a authored over 4 years ago by Roman Bange <[email protected]>68fb89e05203060dba4b1df27f533ce8eace1c5d authored over 4 years ago by Jun Tian <[email protected]>
* Implemented Reinforce policy gradient.
added a experiment with CartPole.
* refactor
*...
9e70733939289efe9ca12931125c4d9feb4295c6 authored over 4 years ago by norci <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
3525d1db1b035c8d55e7b079754f5f68bf166abd 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>
341dabdc122b845c2dbe5c420092003338810ef8 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* add outcome_sampling_mccfr
* add esmccfr
* update README.md
bd6703a2acc6ab02207d42688192e38eae1f8001 authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
97b3cd2a0a796477c8dbd79f711dab0bb73ffb5d authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>Co-authored-by: Your Name <[email protected]>
ed26b0ab123cb4cc7c7e2d9d0d74639d5a220359 authored over 4 years ago by norci <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2e409283a9942c2aeb405ce1488e21124986d4d0 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>
da146c8ffe769f7d2d7eeb94c31ddbc01ab2e424 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* add TD3
* adapt README
ee288a2c65bb23bb9cee753541e097aa30158cd1 authored over 4 years ago by Roman Bange <[email protected]>0c221532744a14f9f83d1ee527e26842e6a94b65 authored over 4 years ago by Jun Tian <[email protected]>
* updated send_to_device, for ElasticArray type.
* recoganize the device of ElasticArray
C...
84f69881701b3d682248c7347f438b4e5a3e44d2 authored over 4 years ago by norci <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
12ed7e625c0e125569e70bb35fcc8a140c3e3d17 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>7ea5cb66ab6bca9e905411baa9f34c14b9d11f8a authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
e3b427f3231a8607a6a5b4c9b0b91080f93f0071 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>358cfc55bc4cebcfd8f8ad4fc4ef293e3da92d6e authored over 4 years ago by Jun Tian <[email protected]>
* fixed typo.
* added test cases for ElasticCompactSARTSATrajectory
* fix test error
* ...
b1082024c332463919317e1186269a064cbc3019 authored over 4 years ago by norci <[email protected]>2e973269a37a0b09eede349d05aeac72404b4e5d authored over 4 years ago by Jun Tian <[email protected]>
* fixed bug in reward logging.
due to multithread env does not have POST_EPISODE_STAGE.
See:...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
a3dc0c97e5c6d40434d5c8a0d4b37505f96e50e2 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>
852b14d0edaaa5d6f9335966920d9bad1050a855 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>
c790052d7978a90c3b5163c568d3e4103033b088 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>b88f12b285da8e48b7e3a9db7f54d9b73ca8c30f authored over 4 years ago by Jun Tian <[email protected]>
* add experiment of snake game
* sync
* add Experiment for Minimax
* add Experiment for...
e0bd4f016446a046c99546f860c283644f5b4c93 authored over 4 years ago by Jun Tian <[email protected]>7c28edee8479e7bb29aeaa86416b4b2dbc6627ff authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
83df811349027049fe150d5078ec862bb620cc07 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>b748da3d15801f4176814e13211d50b1267b4009 authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
de2ac49f86c62378c5cb2df69fdbaeadba16762f authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* bugfixes
572dcd071f8d7ccb66fd32afab5ce7b341d92487 authored over 4 years ago by Jun Tian <[email protected]>* bump version
* minor fix
41b6ec0fde341f681a5d1dec7349099192e1e6e8 authored over 4 years ago by Jun Tian <[email protected]>728f6120fd395ec1d1f009a6077ed20edfe052fd authored over 4 years ago by Jun Tian <[email protected]>
* added Loss values for DDPG policy
* added more tensorboard logs in rl experiments.
adjus...
f775a225cd7fe0fba841672e22fee4e457b6cbcd authored over 4 years ago by norci <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
a744f9d4c789e0d2d421445f995ae66c73ff1dd9 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>
c7c642dea95dc55eb1dc8d40d95c9d714795e239 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* sync
* support MultiAgent with hooks
* fix CFR
* remove dirty code
* fix bug in Ta...
41f9a81a32fd13174df29f1fdaeaebdab0f57d74 authored over 4 years ago by Jun Tian <[email protected]>* add snake game
* update readme
* ignore SnakeGameEnv in test
* refactor OpenSpiel a l...
6e6427d63fbbf67951e58d9d4ffda84ccc90b51f authored over 4 years ago by Jun Tian <[email protected]>* add TabularLearner
* remove extract_experience in learner
* remove extract_experience in...
9453ea34a564d6dd441353c920484a3190ea8afa authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
6cf9010801a74262bf446d7a0b22d70d02bdc9ca authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>b577566c77b3229da424f6bf9db1da189b3cd52d authored over 4 years ago by Jun Tian <[email protected]>
4f203a0925018daeb82cba90060f16fdfb516e38 authored over 4 years ago by Jun Tian <[email protected]>
74057a052d384b70baa975236cff105876b171bd authored over 4 years ago by noreply <[email protected]>
* fix #72
* passing args, kwargs
f4b22cf50dcdf48d3f9dadc35884a5adc45cbcf4 authored over 4 years ago by Jun Tian <[email protected]>b3891d3f7a1122fc48d7ff43fd79e64d53f8b801 authored over 4 years ago by Jun Tian <[email protected]>
fa7aecb6c9bad71a28d0274466494aab7ba0c8f4 authored over 4 years ago by noreply <[email protected]>
* remove TabularRandomPolicy in export
* minor doc fix
9337149ca9d24835efa07e360be86158cf0571e4 authored over 4 years ago by Jun Tian <[email protected]>b22af7b05f7d8c9d05e10f8874eb13d3e10faa60 authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
71a55f1d1a574a5bf018cba7c65949fb7ada44c1 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* remove default behavior of update
* potential bugfix with MultiAgent{n}
* add DefaultSta...
1ca334bd08876ff52af7186275bd8c5188c08031 authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
776ea94e4caf7f68f3ff08a6b2c5cb1aa598228b 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>
d8b64b85a5a7c27a1fdae00de7a09a45bd6bfcc0 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>844ef44f9db402ecd7f90b3c31e14d2b0de2640d authored over 4 years ago by Jun Tian <[email protected]>
87235773369e3d74b01876f7e487c9b2b189f3e1 authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2dbd9ed73e87ff0f0b266a35e4de6cee9661060b authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* add snake game
* update readme
* ignore SnakeGameEnv in test
ce92daabb2ab72a22ce4335b71c124f667a68f78 authored over 4 years ago by Jun Tian <[email protected]>07936108ffadada00241d6f9333884ba0f47043a authored over 4 years ago by noreply <[email protected]>
84d065f800ace0698385bf1dc75943ef13e49351 authored over 4 years ago by Jun Tian <[email protected]>
6ca60d8584a7ab1c98b42a7e9220fea29c0befb4 authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
d3a0e021b3f64d0f7aa537dd35bc4af15ad5cdfe authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* inital SAC implementation
* PR review fixes
bf3d61e5b3dc323463848ec6ba79acd5b603e3bb authored over 4 years ago by Roman Bange <[email protected]>3f41fb80bd1e72ef6c5f814ccca19b72e5b8e304 authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
e24f50c4a99a2e1bc725108f27e4ad87aec1211b 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>
86835ba2059fa5295e40256f95b2cd39f866dbbf authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>c0f31c6c0cc2d866327386eb9a1814a9dc408e7b authored over 4 years ago by Jun Tian <[email protected]>
* add TabularRandomPolicy
* update doc
e64012bb445a14ca46cf9cf37c3a3b7174259502 authored over 4 years ago by Jun Tian <[email protected]>902b42f9d811bbc728b12414dccd72fd6ffa14f9 authored over 4 years ago by noreply <[email protected]>
1812c16bc31e0a6eb1f9e1853577a46fe327d584 authored over 4 years ago by Jun Tian <[email protected]>
861129fe18eaa0ed6bacfb6734502f440dcad563 authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
3b349ab7b37c599b819dcf4ef61580fc553a791d 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>
40d210d95e2b29f7796c7b97a5be89f116d68c14 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>336b49fc4f3a61448453f368eb80f8c6045236f1 authored over 4 years ago by Jun Tian <[email protected]>
* update dependency of RLCore
* remove unnecessary copy due to upstream change
* correct s...
5bf68519e8716e1f477feb0d34168b656b9a0e75 authored over 4 years ago by Jun Tian <[email protected]>b8e43088772b1ea0ccf6735317eaf95825ee2033 authored over 4 years ago by Jun Tian <[email protected]>
* simplify traces
* remove get_trace name
* fix tests
* implement isfull
* deprecate...
883f308d1422fd252fc2e69066db3e6b6eb19b22 authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
6ff61a1f89aa2fcdd109b43c978689f171215f8c authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>96ac5d791f1ce86fb18190de2fc633a7c6daba74 authored over 4 years ago by noreply <[email protected]>
998a72af3bb16db86f41ca8293212c6ac9da8802 authored over 4 years ago by noreply <[email protected]>
7f305d542d2311bbc89816e1b94c854dc68f6c85 authored over 4 years ago by noreply <[email protected]>
* cleanup docs
* use [email protected] for travis test
* use [email protected] for doc build
f541772661e84d72578bbab00dba6558367a07a2 authored over 4 years ago by Jun Tian <[email protected]>0aef7619df5390d949f96d550b0e0386ad2ed31f authored over 4 years ago by Jun Tian <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
d4713774202e0dc5e88a5eb201a934e165cf048a authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* bump version
* fix dependencies
* fix experiments in rl_env
* minor changes of seeds
...
* julia version is limited to v1.4 by CUDA
* update julia version in travis
9f9570727d8c779c56e909e5dbd32220c298f71e authored over 4 years ago by Jun Tian <[email protected]>Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
8c1357b6a4cdcf9c433d65e1b56274e23f972dba authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>* update compat
dea3dbb740f77fbd69674960853ae05f1effcff4 authored over 4 years ago by Jun Tian <[email protected]>* sync
* update RLBase to newer version
* switch to CUDA.jl
* fix more
* fix tests
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
9abae85897a78146bf09671521f1c50a42b19029 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>c992a73ebf78714974c1b3c8ac4b45c12ae75113 authored over 4 years ago by Jun Tian <[email protected]>
* sync
* support next version of RLBase
* fix traits in OpenSpiel
* change seed to rng
...
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
294b185ff48a509ca247278b7326c174fe5b7d14 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>d7ef7f888546b0c4c6f9b06cd42672b27ddf4fea authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
987b49e2af7e038914fd6b2d790e71f6ea770223 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>
554c6aecd18d88e1c40716f41c864f3ced6c6f9c authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>c3e68b39a68f67020b95dbfa0cb6808c383f1f3b authored over 4 years ago by noreply <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
bbb09362be7bb51c82a80773249563b511069a8b authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>8c61b5948d4c3e5f8e4d1984487befd79f63bd7f authored over 4 years ago by noreply <[email protected]>
* support CommonRLInterface
* add tests for ActionStyle
* resolve comments
* Update src...
07a0a6812e0850f608d69392ce0ef58f7550b6e0 authored over 4 years ago by Jun Tian <[email protected]>134617c5e2bb5523ccb4f27b62722404763369a3 authored over 4 years ago by noreply <[email protected]>