github.com/JuliaReinforcementLearning/ReinforcementLearning.jl commits

Updated CHANGELOG.md

4160f8ea5c3668535aa51c428487f066a937906a authored almost 5 years ago by noreply <[email protected]>

CompatHelper: add new compat entry for "CUDAapi" at version "3.1" (#21)

Co-authored-by: Jun Tian <[email protected]>

dd6a3e39f3d912b4c27f9560e53d5f564c2098dd authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Updated CHANGELOG.md

a631d431e3d5889a96c6f4b8bb3b8466e9838302 authored almost 5 years ago by noreply <[email protected]>

CompatHelper: add new compat entry for "MacroTools" at version "0.5" (#19)

Co-authored-by: Jun Tian <[email protected]>

91e701c8d565497b01f689b98b0673229075c342 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Updated CHANGELOG.md

8396fd6394af7eb038677d368bef86605fdd7093 authored almost 5 years ago by noreply <[email protected]>

CompatHelper: add new compat entry for "Distributions" at version "0.22" (#18)

2c859080ba61e5b182f9131ee4ff5012ecb41619 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Update format_pr.yml

71b7aa2a373426e843e75e8a2db1c868bfea8133 authored almost 5 years ago by Jun Tian <[email protected]>

Update CompatHelper.yml

c50fd12e552937b4413a7dc2ee69c2fc2276e818 authored almost 5 years ago by Jun Tian <[email protected]>

format

15c043b6dc6107cd58aa2ba222cffb1a7e50cc03 authored almost 5 years ago by Jun Tian <[email protected]>

Create format_pr.yml

ecdf561761005f224d0c1f8f1d605877512c654f authored almost 5 years ago by Jun Tian <[email protected]>

Updated CHANGELOG.md

e180560a7ffd3b2fdc7a49494034170bd2683751 authored almost 5 years ago by noreply <[email protected]>

Add Some Common Implementations (#16)

The following implementations are added here:

- Spaces
- WrappedEnv
- StateOverriddenObs

d0c6e4c7d92e304b058ad29c9a22aa76fc37a16a authored almost 5 years ago by Jun Tian <[email protected]>

Create CompatHelper.yml

f7b9b27cb228f5c185faafbad751679c2a5f9028 authored almost 5 years ago by Jun Tian <[email protected]>

Install TagBot as a GitHub Action (#53)

b9225fd3c0b9f0297cfe0601368afc663045251f authored almost 5 years ago by Julia TagBot <[email protected]>

Merge pull request #17 from JuliaTagBot/master

Install TagBot as a GitHub Action

8b2dad0c34d20b8083949a244730eb2737a2294b authored almost 5 years ago by Jun Tian <[email protected]>

Install TagBot as a GitHub Action (#19)

73a36b527da2d3d403ed884b4f6d1be82dc6ba59 authored almost 5 years ago by Julia TagBot <[email protected]>

Install TagBot as a GitHub Action (#30)

784954b34c74db36a33b7bfd0e665b180d3d74c2 authored almost 5 years ago by Julia TagBot <[email protected]>

Install TagBot as a GitHub Action

43d2fb86e722f1afa894e1252b2c41073e4407f9 authored almost 5 years ago by Julia TagBot <[email protected]>

Updated CHANGELOG.md

7590e893f923628d58e4e978bd3d243aa76bddc4 authored almost 5 years ago by noreply <[email protected]>

Update format_pr.yml

b4607ef91c249b159f8ad65a203748cdc7ea8369 authored almost 5 years ago by Jun Tian <[email protected]>

Update README.md

b151f5176d3330b86aab63037848e0d9693cee93 authored almost 5 years ago by Jun Tian <[email protected]>

CompatHelper: add new compat entry for "Reexport" at version "0.2" (#10)

Co-authored-by: Jun Tian <[email protected]>

5c4537d6714db38884a7d2ee9790b8409cc0a3d8 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "StatsBase" at version "0.32" (#12)

Co-authored-by: Jun Tian <[email protected]>

faaaa88e1409e6ed88fbe46fff75a7e3a2a8fc49 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "MacroTools" at version "0.5" (#14)

Co-authored-by: Jun Tian <[email protected]>

701401e538b3c5c5e39f88918452ff588ca637f8 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "ProgressMeter" at version "1.2" (#15)

Co-authored-by: Jun Tian <[email protected]>

e228b1455824dad509fac207beb5737102422720 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "Distributions" at version "0.22" (#16)

Co-authored-by: Jun Tian <[email protected]>

9562818735d26e2543cc042d1d43d9854acc5662 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "ReinforcementLearningBase" at version "0.5" (#13)

Co-authored-by: Jun Tian <[email protected]>

014d18bb41b1967273850a16ace9f70ca07cb56c authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "CuArrays" at version "1.7" (#9)

Co-authored-by: Jun Tian <[email protected]>

05e4e419fd730cecb0af724373e8255a908401a6 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for "Flux" at version "0.10" (#11)

c87f25b44c342c92e804074478a0d9214f135d6b authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Initial Commit (#8)

c1ac7d04b3bb5e59f51f5ad9b92a6624f038c2bc authored almost 5 years ago by Jun Tian <[email protected]>

Update changelog.yml

847cada164dd55bebaf3321fdcc31320c35c1432 authored almost 5 years ago by Jun Tian <[email protected]>

Create CompatHelper.yml

7be4aa4e9c5ee3d879d47cfa1c4f74c0454a5671 authored almost 5 years ago by Jun Tian <[email protected]>

Updated CHANGELOG.md

03a3fc3700125bcf17c7ba50caeab90cb47ad104 authored almost 5 years ago by noreply <[email protected]>

Create format_check.yml

d216e68e155f6bf1b72b28fe822535b0c384c6fa authored almost 5 years ago by Jun Tian <[email protected]>

Create changelog.yml

81379416a84734a9331cf515b6979f3c80971a64 authored almost 5 years ago by Jun Tian <[email protected]>

Update Project.toml

5ccd3db3f14771ef63c31aafaf94221bc9b60177 authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #12 from findmyway/add_pop

add pop! method for AbstractTrajectory

69c53cf1a8e84ab46c5aab1ca552d26f3d1faccb authored almost 5 years ago by Jun Tian <[email protected]>

merge master

47f6f315d26c991aa1baff30549aa1b7d4125ecc authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #13 from findmyway/change_push

change the default implementation of push! for trajectory

41279c4569da6b0ed83a24cec65994749e40819f authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #14 from findmyway/change_action_style

make ActionStyle return MINIMAL_ACTION_SET by default

22f9cefafeb5b529a7374d7c2bfe929ab381ed97 authored almost 5 years ago by Jun Tian <[email protected]>

format

746e75b6dd49735871b2a994f6e8dec2d797832b authored almost 5 years ago by Jun Tian <[email protected]>

make ActionStyle return MINIMAL_ACTION_SET by default

191265ffab272f03b3684de08fee0627940b9274 authored almost 5 years ago by Jun Tian <[email protected]>

change the default implementation of push! for trajectory

429ff26fa267d056b425351d565779f07eaf774e authored almost 5 years ago by Jun Tian <[email protected]>

add pop! method for AbstractTrajectory

2edeac94969e6f944cf4cbad2fdbc26b42a404b6 authored almost 5 years ago by Jun Tian <[email protected]>

Updated CHANGELOG.md

b9aba016a20310019921712fc97f50f3e04c2595 authored almost 5 years ago by noreply <[email protected]>

Update Project.toml

bd718f3613a03918a169483d7a10a900c676e7df authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #10 from findmyway/update_interface

add two extra stages

ae1b772e96e7851a13804536a72db4d40debb614 authored almost 5 years ago by Jun Tian <[email protected]>

add two extra stages

4da34f8d164597461df4a507a740208e2e7bab2d authored almost 5 years ago by Jun Tian <[email protected]>

Updated CHANGELOG.md

a6e216610f13676d8f4750c6b96cf6141ba1d57f authored almost 5 years ago by noreply <[email protected]>

Update changelog.yml

9c8534aa3c2afb8a2fe69fe81459c1a1e0cd8aad authored almost 5 years ago by Jun Tian <[email protected]>

Update changelog.yml

ecf7d5d8158df490ceddd31e84f9d73a21044c1e authored almost 5 years ago by Jun Tian <[email protected]>

Create changelog.yml

ab912f69c7b922531988fdfc8374322546a01def authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #8 from JuliaReinforcementLearning/create-pull-request/format-pr-aedb2a7

[AUTO] Format .jl files

499fcd9cc314bc39b0b4e75e857dc0c006a817ff authored about 5 years ago by Jun Tian <[email protected]>

Format .jl files

b5592446c37f38f05b3bcf0e83c35a2dc5d38d06 authored about 5 years ago by findmyway <[email protected]>

Create format_check.yml

aedb2a7884d295a563a636ffbca9638b3b029da9 authored about 5 years ago by Jun Tian <[email protected]>

Create format_pr.yml

007c979077624222696bfa19307dd0177b310267 authored about 5 years ago by Jun Tian <[email protected]>

Update Project.toml

62afd3a150d6e42ba16b4d9b8e5816989bff6ab6 authored about 5 years ago by Jun Tian <[email protected]>

Update Project.toml

b92eb8fb972da9b8f24132b51ff56c28d92eb5bc authored about 5 years ago by Jun Tian <[email protected]>

Update Project.toml

f55e1de6639f46c126d34af13c61a9ad207dce47 authored about 5 years ago by Jun Tian <[email protected]>

Merge pull request #6 from findmyway/redesign

Redesign

70436b02179ab07b5947b4aabc0aade3eea02f45 authored about 5 years ago by Jun Tian <[email protected]>

sync

c0c5b5442274710dd07eedb4b17ee9395e3c5d7e authored about 5 years ago by Jun Tian <[email protected]>

support mask for explorers

90bcdee9b1a8ef4c895733eb29e3f1d02a3aec57 authored about 5 years ago by Jun Tian <[email protected]>

pass tests

4b22eb58d0b269fde9341c505cbcb882d888ef91 authored about 5 years ago by Jun Tian <[email protected]>

init

e789b2ce5ffdb45af0a7f410521a6d3e88c386d6 authored about 5 years ago by Jun Tian <[email protected]>

update

496fd2c444801639f9368c952c460f8b860771fb authored about 5 years ago by Jun Tian <[email protected]>

update compat

cbe5a85f8920e60891d733aa33fdfd8dd84f96ac authored about 5 years ago by Jun Tian <[email protected]>

update

421f9acd1c954eb5b1968c3bc885bf180e7b4a4e authored about 5 years ago by Jun Tian <[email protected]>

Merge remote-tracking branch 'upstream/master' into redesign

98b5d3577ef75f3a70a4a7c08b680efa9a003a90 authored about 5 years ago by Jun Tian <[email protected]>

init

5e2a619309201733255d8164d3e7d5066264c1e0 authored about 5 years ago by Jun Tian <[email protected]>

Files generated by PkgTemplates

63aacef7e9725634396b45e7660cac7765002fc2 authored about 5 years ago by Jun Tian <[email protected]>

Initial commit

134c9da6083ff6ca9db61356b2e130f499712cbb authored about 5 years ago by Jun Tian <[email protected]>

update benchmark for circular_array_buffer (#50)

* update benchmark for ccircular_array_buffer

* increase about 40%

* rainbow is still slow...

aae24d5e107939048440561e912c73ca0e8519f9 authored about 5 years ago by Jun Tian <[email protected]>

update dependencies and docs (#49)

515ae65ef02990c5a7b0370a1515a3186850a731 authored about 5 years ago by Jun Tian <[email protected]>

update dependencies (#48)

* update dependencies

76c2542d6e10eb0a5d727a737d11dd0ef03051c3 authored about 5 years ago by Jun Tian <[email protected]>

add more docs

5c10dba7fd85b15c8e10e826425c5be614c6aeb0 authored about 5 years ago by Jun Tian <[email protected]>

fix bug in rainbow (#47)

af0159254e112b8e546cc0a48f3909a1aa9b8fad authored about 5 years ago by Jun Tian <[email protected]>

fix example in doc && update examples (#46)

* fix example in doc && update examples

* the rainbow is quite slow, need revisit in the next...

a70c73721fac9d1627db7c86c23efc84d4ff382c authored about 5 years ago by Jun Tian <[email protected]>

Refactor buffer (#45)

* sync

* ready to update learners

* add StakFrames preprocessor

* critical bug fix

*...

307041f81488db815efc0811e9284487a2916f58 authored about 5 years ago by Jun Tian <[email protected]>

correct format in compat

d6622e469d0f63cd126a10a7e0f9fef4db2f99d6 authored about 5 years ago by Jun Tian <[email protected]>

add upper bound for dependencies

e30dd92a4194392de4d02852836b30bf57ba5cf5 authored about 5 years ago by Jun Tian <[email protected]>

Update Project.toml

a87c1050e046df599ef8be1bec432b1c40b27982 authored about 5 years ago by Jun Tian <[email protected]>

update atari env to use max-pooling (#22)

* update atari env

* add test cases for atari environments

* add doc

274aec6515889d1ba27407b7c9fe9446d66fb1c0 authored about 5 years ago by Jun Tian <[email protected]>

Create pull_request_template.md

a4e077d6d50536aa7289830fca36feda804002e9 authored about 5 years ago by Jun Tian <[email protected]>

export AbstractActionSelector and add more comments (#42)

* export AbstractActionSelector and add more comments

* update test cases

c66bbc8e46d3715326d3f137250a93a1b8ad7636 authored about 5 years ago by Jun Tian <[email protected]>

add docs (#39)

* add docs

3025a3f833ff7e70c7223ef46d339b49a0acde14 authored about 5 years ago by Jun Tian <[email protected]>

Support both Knet and Flux(with Zygote) (#38)

* support Knet

* add Manifest.toml file to allow developers to reproduce experiments

5c260630d4397fe0f01c6aa64bde771057289278 authored over 5 years ago by Jun Tian <[email protected]>

Switch Tracker.jl to Zygote.jl (#37)

* add huber_loss

* rename q-learner to BasicDQNLearner

* todo: bugfix

* sync

* fix b...

96d7898550e2e0ad91a039d5fe402c08f654c5bf authored over 5 years ago by Jun Tian <[email protected]>

Bump version to v0.1.2

7b9fea07b6164f85e7ad9aeed1dd3c1387a00ac4 authored over 5 years ago by Jun Tian <[email protected]>

Merge pull request #21 from JuliaReinforcementLearning/update_cart_pole

Update cart pole environment to allow reaching the max_step

8fa6683c168a53bb49772732e242ec37435e01f9 authored over 5 years ago by Jun Tian <[email protected]>

allow cart pole environment to reach the max_step

1e72a4283cc1049162375f0fc1398ac72acae915 authored over 5 years ago by Jun Tian <[email protected]>

auto format code

4e955e924969a4b145594a89aba664704cd97c99 authored over 5 years ago by Jun Tian <[email protected]>

[WIP] bugfix and api simplification (#34)

574bd419289997533325c38bc1bc2e965f684806 authored over 5 years ago by Jun Tian <[email protected]>

use new api in ReinforcementLearningEnvironments.jl (#33)

* fix errors due to dependency change

* pin Flux to v0.8.3

4b8b4779fbe2f7164e18a27c3553f9c44b4a168b authored over 5 years ago by Jun Tian <[email protected]>

Bump version to v0.1.1

4f69df7d41efcb1b1c3e467e79bf25450698254c authored over 5 years ago by Jun Tian <[email protected]>

Api change (#19)

* unify interfaces

* update screen after interact

* add minor comment

* add version che...

243ce2cfcb7f46868b8bdcc82e3af19a9f8667d1 authored over 5 years ago by Jun Tian <[email protected]>

add rainbow (#31)

* add rainbow

65a5e0a1caf06cea1bc070b5dc71cf2e7be66b2a authored over 5 years ago by Jun Tian <[email protected]>

add double dqn (#30)

d4645301de7fe02e0a5a214dea17287d05f473d9 authored over 5 years ago by Jun Tian <[email protected]>

bugfix

ecfa5f37c4c4c46feb57097f4027891150e2fd0c authored over 5 years ago by Jun Tian <[email protected]>

Prioritized dqn (#29)

* add PRTSA

* add prioritized dqn

3aa43d804fe4bec148a0ef37e1d8656609cc6f41 authored over 5 years ago by Jun Tian <[email protected]>

remove some old components

dcf3d81b5ebf028b9245b20b2a9fd0ae2361b337 authored over 5 years ago by Jun Tian <[email protected]>

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl