issues
search
DeepX-inc
/
machina
Control section: Deep Reinforcement Learning framework
MIT License
279
stars
43
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Support gym.spaces.Dict
#216
iory
opened
5 years ago
2
[pds/multi_categorical_pd.py] Fix bug of Multi categorical probabilistic distribution
#215
rarilurelo
closed
5 years ago
0
Use default device manager in PyTorch
#214
rarilurelo
opened
5 years ago
0
Make document pages
#213
takerfume
closed
5 years ago
3
Add Import
#212
iory
closed
5 years ago
1
[algos/qtopt] Make iterator called only once
#211
iory
closed
5 years ago
2
Fixed random_batch in Traj class
#210
iory
closed
5 years ago
1
Add option of bptt's length
#209
rarilurelo
opened
5 years ago
0
Add r2d2 link
#208
takerfume
closed
5 years ago
0
Add web page link
#207
takerfume
closed
5 years ago
0
Add option
#206
takerfume
closed
5 years ago
0
[WIP] Add Ring buffer
#205
iory
opened
5 years ago
0
Add rnn and dp il
#204
takerfume
closed
5 years ago
0
fix
#203
rarilurelo
closed
5 years ago
0
Dataparallel Option in PPO Cause Error
#202
takerfume
closed
5 years ago
2
change name of library for pip
#201
rarilurelo
closed
5 years ago
0
Add algo matrix
#200
takerfume
closed
5 years ago
3
fix to be able to pass epi to ef
#199
rarilurelo
closed
5 years ago
0
fix mean of loss with rnn option
#198
rarilurelo
closed
5 years ago
0
Fast sampling for random batch
#197
rarilurelo
closed
5 years ago
1
Add option traj allocation
#196
rarilurelo
closed
5 years ago
0
[optims] Add distributed SGD
#195
iory
closed
5 years ago
1
add explanation of r2d2
#194
rarilurelo
closed
5 years ago
0
TD3
#193
takerfume
opened
5 years ago
1
Fix options for ppo and trpo with rnn
#192
takerfume
closed
5 years ago
4
Implement R2D2 (SAC ver.)
#191
jinbeizame007
closed
5 years ago
1
Add random batch rnn
#190
jinbeizame007
closed
5 years ago
1
update readme
#189
rarilurelo
closed
5 years ago
0
Change num expert epis from 100 to 2
#188
takerfume
closed
5 years ago
1
remove unnecessary curl code
#187
pwuethri
closed
5 years ago
2
hoge
#186
rarilurelo
closed
5 years ago
0
update merits
#185
rarilurelo
closed
5 years ago
0
add link to examples
#184
rarilurelo
closed
5 years ago
0
Update readme algorithms
#183
takerfume
closed
5 years ago
1
update readme add algorithms
#182
rarilurelo
closed
5 years ago
0
fix license
#181
rarilurelo
closed
5 years ago
0
Example code does not run anymore
#180
pwuethri
closed
5 years ago
1
Faster sampling in random batch
#179
rarilurelo
closed
5 years ago
1
Add no noise option for ddpg
#178
takerfume
closed
5 years ago
3
Add data parallel for qtopt
#177
takerfume
closed
5 years ago
2
Add N-distill
#176
pwuethri
opened
5 years ago
1
Fix for using gpu in qtopt
#175
takerfume
closed
5 years ago
3
Add entropy regularised policy distillation
#174
pwuethri
closed
5 years ago
7
Update readme
#173
pwuethri
closed
5 years ago
1
Data parallel on CEMDeteminisiticSAVfunc
#172
rarilurelo
closed
5 years ago
1
Rename lf.likelihood
#171
takerfume
closed
5 years ago
0
fix #140
#170
ven-kyoshiro
closed
5 years ago
2
Update contribute
#169
rarilurelo
closed
5 years ago
0
`lf.likelihood` seems to be log-likelihood
#168
rarilurelo
closed
5 years ago
2
More general hs (hidden state)
#167
rarilurelo
opened
5 years ago
0
Previous
Next