issues
search
DeepX-inc
/
machina
Control section: Deep Reinforcement Learning framework
MIT License
279
stars
45
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Add benefit samplecode
#116
rarilurelo
closed
5 years ago
0
Add offandon samplecode
#115
rarilurelo
closed
5 years ago
0
Wrapper environment in which observation includes reward
#114
rarilurelo
closed
5 years ago
1
Wrapper environment in which observation includes action
#113
rarilurelo
closed
5 years ago
1
add contribution guide
#112
rarilurelo
closed
5 years ago
2
Implementation of R2D2
#111
rarilurelo
closed
5 years ago
1
fix
#110
rarilurelo
closed
5 years ago
0
fix
#109
rarilurelo
closed
5 years ago
0
add documents on #98
#108
ven-kyoshiro
closed
5 years ago
1
Fix dp run
#107
rarilurelo
closed
5 years ago
0
0.10.5
#106
rarilurelo
closed
5 years ago
0
fix
#105
rarilurelo
closed
5 years ago
0
add original env
#104
rarilurelo
closed
5 years ago
0
Transparent environment
#103
rarilurelo
closed
5 years ago
1
Add async plot in logger
#102
rarilurelo
closed
5 years ago
1
add sleep
#101
rarilurelo
closed
5 years ago
1
Diversity is All You Need: Learning Skills without a Reward Function
#100
ven-kyoshiro
closed
5 years ago
2
Update README.md
#99
pwuethri
closed
5 years ago
1
quick startの説明
#98
rarilurelo
closed
5 years ago
1
contribution guide
#97
rarilurelo
closed
5 years ago
2
Add links to readme
#96
rarilurelo
closed
5 years ago
0
Fix quick start
#95
rarilurelo
closed
5 years ago
0
loggerのplotで、学習時間が多くなると、csv読み込みに時間がかかる
#94
rarilurelo
closed
5 years ago
1
Creating model based policy
#93
rarilurelo
opened
5 years ago
2
EpiSamplerでの待機時に、sleepを入れると、cpu占有率が下がるのではないか?
#92
rarilurelo
closed
5 years ago
1
Change license
#91
rarilurelo
closed
5 years ago
0
update readme
#90
rarilurelo
closed
5 years ago
0
machinaの利点を反映させたサンプルコードを作成する
#89
rarilurelo
closed
5 years ago
1
Sphinx
#88
rarilurelo
closed
5 years ago
0
add sphinx
#87
rarilurelo
closed
5 years ago
0
Quickstart
#86
ven-kyoshiro
closed
5 years ago
6
detachを使っているところで、torch.no_gradを使う
#85
rarilurelo
closed
5 years ago
0
Add docstring
#84
rarilurelo
closed
5 years ago
0
epi_functionalの引数が、trajになっているが、episodesをそのまま渡すほうがしっくりくる
#83
rarilurelo
closed
5 years ago
1
Add autopep test
#82
rarilurelo
closed
5 years ago
0
Gather misc to logger
#81
rarilurelo
closed
5 years ago
0
performance check
#80
rarilurelo
opened
5 years ago
0
argument of reduction in loss_functional
#79
rarilurelo
opened
5 years ago
0
fix
#78
rarilurelo
closed
5 years ago
0
Implement Prioritized Experience Replay
#77
jinbeizame007
closed
5 years ago
2
Implement Behavioral Cloning and GAIL
#76
takerfume
closed
5 years ago
11
OUActionNoiseの引数について
#75
rarilurelo
closed
5 years ago
2
None Error in Categorical and rnn policy with cpu
#74
rarilurelo
closed
5 years ago
0
add ppo
#73
rarilurelo
closed
5 years ago
0
Saving method in Traj class
#72
rarilurelo
opened
5 years ago
0
Update pds
#71
rarilurelo
closed
5 years ago
1
fix
#70
rarilurelo
closed
5 years ago
0
rename samples and remove prepro
#69
takerfume
closed
5 years ago
1
add soft actor critic's alpha
#68
rarilurelo
closed
5 years ago
0
Multi-node Sampler
#67
rarilurelo
closed
5 years ago
1
Previous
Next