issues
search
yandexdataschool
/
AgentNet
Deep Reinforcement Learning library for humans
http://agentnet.rtfd.org/
Other
301
stars
71
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Original DQN Example
#103
ehknight
opened
7 years ago
1
Update install.md
#102
tigerneil
closed
7 years ago
1
Rollback recurrence
#101
justheuristic
closed
7 years ago
0
Develop
#100
justheuristic
closed
7 years ago
0
attention tests
#99
justheuristic
closed
7 years ago
1
Fixing Issue #94 (problems with deepcopy of DictLayer in python3)
#98
tswr
closed
7 years ago
0
relax assert
#97
justheuristic
closed
7 years ago
0
Destination GpuArray is not contiguous
#96
kashif
closed
7 years ago
5
batch_size parameter is wierd
#95
pshvechikov
closed
7 years ago
1
Targetnet of layer on top of LSTMCell results in deepcopy error
#94
pshvechikov
closed
7 years ago
3
policy_estimators param is weird
#93
pshvechikov
closed
7 years ago
3
Support both Theano (Lasagne; Keras) and Tensorflow (Keras) backend
#92
Omrigan
opened
7 years ago
1
BaseResolver returns int64
#91
justheuristic
closed
7 years ago
1
deprecate preprocess_observation
#90
justheuristic
closed
7 years ago
1
Vectorized environment
#89
justheuristic
opened
7 years ago
0
Optimality tightening
#88
sidorov-ks
closed
7 years ago
0
Optimailty tightening
#87
sidorov-ks
closed
7 years ago
1
DPG refactor and demo
#86
justheuristic
closed
7 years ago
1
Refactored docstrings + pep8 + some DRY
#85
persiyanov
closed
7 years ago
0
better weights management for memory layers
#84
justheuristic
opened
7 years ago
0
grad dtypes mismatch in some rare case
#83
justheuristic
closed
7 years ago
2
Update .travis.yml
#82
justheuristic
closed
7 years ago
1
example:Qlearning with normalized advantage functions
#81
justheuristic
closed
7 years ago
1
canonicalize LSTM
#80
justheuristic
closed
8 years ago
3
AgentNet recurrence won't compile if batch_size = 1 and unroll_scan=False and at least one input is a single-element vector.
#79
justheuristic
closed
7 years ago
2
Added link to the documentation in the text
#78
arogozhnikov
closed
8 years ago
0
Brief outline of modules
#77
arogozhnikov
closed
8 years ago
3
починить рекурсию при разных batch size
#76
Avidereta
closed
8 years ago
0
sync develop
#75
justheuristic
closed
8 years ago
0
Patch 2
#74
Mariewelt
closed
8 years ago
0
Update session_pool.py
#73
Mariewelt
closed
8 years ago
0
Experience replay added to the session pool
#72
Mariewelt
closed
8 years ago
0
Hierarchical MDP as a demo?
#71
justheuristic
opened
8 years ago
0
Всякая мелочь
#70
justheuristic
closed
8 years ago
0
Dockerfile aka "makeitwork"
#69
justheuristic
closed
8 years ago
0
Deprecation list
#68
justheuristic
closed
7 years ago
0
convergence tests
#67
justheuristic
closed
8 years ago
0
Minimal initial example
#66
arogozhnikov
closed
8 years ago
1
better basic example
#65
justheuristic
closed
8 years ago
1
crop @ all RL methods
#64
justheuristic
closed
8 years ago
1
one-line install and a few description lines
#63
justheuristic
closed
8 years ago
0
DictLayer minimalistic
#62
justheuristic
closed
8 years ago
0
Working environment for AgentNet on travis-CI
#61
arogozhnikov
closed
8 years ago
0
minimal automated test
#60
arogozhnikov
closed
8 years ago
0
updated README
#59
arogozhnikov
closed
8 years ago
0
TODOs
#58
justheuristic
closed
8 years ago
0
Reformatting / reindentation
#57
arogozhnikov
closed
8 years ago
1
initial refactor
#56
arogozhnikov
closed
8 years ago
0
TupleLayer refactor
#55
justheuristic
closed
8 years ago
1
Automated tests on convergence
#54
arogozhnikov
closed
8 years ago
3
Next