github.com/JuliaReinforcementLearning/ReinforcementLearningZoo.jl commits

Format .jl files (#56)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

0867888c6a0e505aaa51373dd91808ed7f013623 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

resolve performance issue when calculating loss (#58)

* resolve performance issue when calculating loss

* decrease number of params in JuliRL_DDPG_...

9d29297f9748d1de3344e034b1d7e51b40f3ff23 authored over 4 years ago by Jun Tian <[email protected]>

add BasicDQN and DQN experiments with MountainCarEnv (#57)

36492f101e477b83e59c40461c147cf461bcc86d authored over 4 years ago by Felix Chalumeau <[email protected]>

Update Project.toml

f33ee4496e9e58c26e5d0e76b3697e42c1e77c5e authored over 4 years ago by Jun Tian <[email protected]>

Reward clip in Atari environments (#55)

* allow setting maximum frames in atari env

* clip reward in Atari experiments

f5ab68e8d4a5aedf07df93451b07fa5583a5061a authored over 4 years ago by Jun Tian <[email protected]>

allow setting maximum frames in atari env (#54)

5e1eeb53ab3d73897d9be048da4b93179c0cf021 authored over 4 years ago by Jun Tian <[email protected]>

Update .travis.yml

df7498df7eb8999734b92cf799e1d25661e7d1db authored over 4 years ago by Jun Tian <[email protected]>

fix (#53)

c8ebdd9b1299071f2a6fd004eb32700499c6c891 authored over 4 years ago by jbrea <[email protected]>

Update Project.toml

424da59180d22113e6a67ba045f303b1d3fa087e authored over 4 years ago by Jun Tian <[email protected]>

Update .travis.yml

df8dc0b7de44e84863ee22ab76edf94f7d94026c authored over 4 years ago by Jun Tian <[email protected]>

resolve warning (#50)

7ec6b2104cf91c0aa27de1359023cf372e484c5a authored over 4 years ago by Jun Tian <[email protected]>

Revert version

e66bf70732e51a332a11d44fe6ee899e9bd3c645 authored over 4 years ago by Jun Tian <[email protected]>

bump version

2d872a50302fb34e9c2adde05cdb11a9a2c81278 authored over 4 years ago by Jun Tian <[email protected]>

udpate doc for learners/policies (#49)

7b246bc7caf3b68b70c46b08888c9cdc38a4c871 authored over 4 years ago by Jun Tian <[email protected]>

CompatHelper: add new compat entry for "CuArrays" at version "2.2" (#37)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

a955648238f34040c6593437b0e5085e0da6814c authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

add a list of available experiments (#48)

3356d0f8d8acdd99b95f330aa563134a0e45938a authored over 4 years ago by Jun Tian <[email protected]>

CompatHelper: add new compat entry for "MacroTools" at version "0.5" (#47)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

679be7f42e62ed44f4b79eebf7b8d517321e24bf authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Format .jl files (#46)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

9ba7e4d880252bf5b170ae6c703c3b7ce8ae8714 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Add PPO (#14)

* add PPO

* revert changes

* add an experiment of PPO on CartPole

* add ppo

* add PP...

9655d3c8ada46cf2fda2ef78ff952486be8de966 authored over 4 years ago by Jun Tian <[email protected]>

Format .jl files (#42)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

2a493a8a9623aa279d7efde93a57dd5c58216ea2 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Add DDPG (#16)

* add ddpg

* export DDPGPolicy

* add experiment for DDPG

* remove unused test file

*...

f5a3706167f9a1e1d049513cb6c2172c2292e5b3 authored over 4 years ago by Jun Tian <[email protected]>

Format .jl files (#41)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

ee8c4c7ba6ac8721594a7568883d6492e03aefb5 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

bugfix with A2C (#40)

* bugfix with A2C

* add experiment for A2CGAE

* only update A2CGAE in Training mode

671fe88af11da4d3040595e278b5a1d7eff75040 authored over 4 years ago by Jun Tian <[email protected]>

Format .jl files (#31)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

03b4345ff825da3f25afa3b3161e42f86767b416 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

remove seed in experiments (#39)

5c120d05c53508818e7266f604f50a17e9517f44 authored over 4 years ago by Jun Tian <[email protected]>

Add experiment for IQN (#38)

* add IQN

* uncomment tests

* fix method missing error

* add atari experiment for iqn &...

4a5f9b90953b24d806277b3f905094e5dab5cd43 authored over 4 years ago by Jun Tian <[email protected]>

add IQN (#36)

* add IQN

* uncomment tests

* fix method missing error

d006d2ab7ec0044a0b99c5934126a250e4e454de authored over 4 years ago by Jun Tian <[email protected]>

potential bug fix (#35)

89851469ce170ef7815b525dfdd779f596b4e618 authored over 4 years ago by Jun Tian <[email protected]>

fix bug in PrioritizedDQN and Rainbow (#34)

5f96fcf1d463bce3e02c1195fc98de225d3a55d6 authored over 4 years ago by Jun Tian <[email protected]>

add artifacts (#30)

* add artifacts

* add test case for pretrained models

* bugfix

f19ea344288e1820534425f0893a8e6e8b75f4a5 authored over 4 years ago by Jun Tian <[email protected]>

Format .jl files (#29)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

0f544ea5cb1dddf039da95639c22ad6f2ca91ece authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

minor bugfix and add experiment for Rainbow (#28)

f6bba8b4e79088128c4ca6443c4786458437e968 authored over 4 years ago by Jun Tian <[email protected]>

Udpate compat (#27)

* CompatHelper: add new compat entry for "BSON" at version "0.2"

* CompatHelper: add new comp...

fd436b5d8a34117e4782478cba7ac70e951414f2 authored over 4 years ago by Jun Tian <[email protected]>

Format .jl files (#18)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

34b5cd7ca7d71a6609c136e9aea52d716f13114a authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Update dependency of RLBase and RLCore (#21)

* update due to upstream change

* sync

* rainbow slow on GPU is fixed

* update A2C

*...

cacc5cc5303dcce5f18ef15fca45a36c64be3e11 authored over 4 years ago by Jun Tian <[email protected]>

Minor bug fixes (#15)

Fixed few bugs

92ee1d499125730404873afb25043c74bb465e1e authored almost 5 years ago by Sriram <[email protected]>

Format .jl files (#13)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

3436e3e7c66b439089158d67903f348a6fdcc96c authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Added A2CGAE (#8)

* Added A2CGAE

Added Actor Critic with generalized advantage estimation

* bugfix in A2C

...

380847f3cf84442a1ff6178a5fdcdbfde2987459 authored almost 5 years ago by Sriram <[email protected]>

Merge pull request #10 from findmyway/dev_actor_critic

Fix bug in A2CLearner

43818939b8f337e3ccf2fc55cf145e6815322f9e authored almost 5 years ago by Jun Tian <[email protected]>

Update A2C.jl

1cbafd2f1de715bfd9e53c91a730552a4fc94d00 authored almost 5 years ago by Jun Tian <[email protected]>

use gpu by default

d5a0d0995d8cc4139af2c989f645be531dbd46f0 authored almost 5 years ago by Jun Tian <[email protected]>

sync

a97577d26233785dffcc2d63976e9a3ebba1f5d3 authored almost 5 years ago by Jun Tian <[email protected]>

bug fix

204412aee02694846e6eb4aecb77fd4c3c6e25ce authored almost 5 years ago by Jun Tian <[email protected]>

merge master

757f40e93d09e542b8549ad7cf8b703b70816bac authored almost 5 years ago by Jun Tian <[email protected]>

bugfix in A2C

2fbb54d235c7633a42e87017144f4fce6c8cee01 authored almost 5 years ago by Jun Tian <[email protected]>

Delete format_check.yml

1dfd2e821189f538d62e9b4a21605ffd07712ce1 authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #4 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

c18bb41b0d7c80a57d7dccf7235b01944e1da442 authored almost 5 years ago by Jun Tian <[email protected]>

Format .jl files

3d52a5a1f8869c2f3dc3815c48cc0470bc518da5 authored almost 5 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Merge pull request #3 from findmyway/dev_actor_critic

add A2C

9370feec5e4065d5676375e50a003f76ff34ab36 authored almost 5 years ago by Jun Tian <[email protected]>

add A2C

a8dcf3b96b373b7daa8bf8376595720fd29aebb1 authored almost 5 years ago by Jun Tian <[email protected]>

Update Project.toml

4dbfe045633aede941102c5b3cc8a4a893584f2c authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #2 from findmyway/update_doc

add doc

19fb820a13b0ffadecf97d1613a9632bdf182c41 authored almost 5 years ago by Jun Tian <[email protected]>

add doc

82933ddb20d24f9ba71efc092934d8dc106f08d9 authored almost 5 years ago by Jun Tian <[email protected]>

Update README.md

35c13cd120cd7e2a304b406c7135c68f8a726aef authored almost 5 years ago by Jun Tian <[email protected]>

Update README.md

57cbbbe17b9b33e69e233f7dc08771bd2f75519a authored almost 5 years ago by Jun Tian <[email protected]>

Update README.md

42e0007e0a003b954a24c29fd8e49c9caf8aac0f authored almost 5 years ago by Jun Tian <[email protected]>

Update README.md

a5e228ad23f0096d3b7c76b8296156833162a7a1 authored almost 5 years ago by Jun Tian <[email protected]>

Merge pull request #1 from findmyway/master

add DQN

fc391c05b7b2f4d05e8bcbe455bce4b06270d71f authored almost 5 years ago by Jun Tian <[email protected]>

update julia version in travis

8868ed5e2f2c4dfe725bec82f2bd4b0d08f365f9 authored almost 5 years ago by Jun Tian <[email protected]>

update compat

92f27e5cfa8ab6a6ed275d00019301c71a92e253 authored almost 5 years ago by Jun Tian <[email protected]>

add github actions

d890f36ed8f40a2e8268ae5ecd403c7b47ea03a6 authored almost 5 years ago by Jun Tian <[email protected]>

fix test error

d7ccaf8ec6680fe8c2981b13ebde1d1fb5003859 authored almost 5 years ago by Jun Tian <[email protected]>

clean dependency

f66350c5501aa32b824c29207841939a1b27acfb authored almost 5 years ago by Jun Tian <[email protected]>

format

db3c36ea2b0e55ae91c29de6b71345abbf674334 authored almost 5 years ago by Jun Tian <[email protected]>

add Rainbow

e35324a3948e17af162cfe616ffeb1364c76366d authored almost 5 years ago by Jun Tian <[email protected]>

add PrioritizedDQN

ea0780281d96a3592364b932e0d47dce0b14b08f authored almost 5 years ago by Jun Tian <[email protected]>

add dqn

dfe180d94d4a7639471ba98789f44758d83e6fea authored almost 5 years ago by Jun Tian <[email protected]>

add BasicDQN

8303e3cfa9c35aef52d705caeaf89e58a3bdfd91 authored almost 5 years ago by Jun Tian <[email protected]>

Files generated by PkgTemplates

d876d721854ed464754399bfbba26268f687f450 authored almost 5 years ago by Jun Tian <[email protected]>

Initial commit

d698d273164444f48544ebb34f7f802ce35a7b7e authored almost 5 years ago by Jun Tian <[email protected]>

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearningZoo.jl