issues
search
hal3
/
macarico
learning to search in pytorch
MIT License
111
stars
12
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
requirements?
#39
andreasvlachos
opened
5 years ago
9
Enable training reslope with trainloop_ppo
#38
amrsharaf
closed
6 years ago
0
Clean-up + Call trainloop_ppo when a learner of type PPO is used in trainloop
#37
amrsharaf
closed
6 years ago
0
PPO support for multiple epochs and mini-batch sizes
#36
amrsharaf
closed
6 years ago
0
Completed issue 31: Support Reward Per time-step
#35
xkianteb
opened
6 years ago
6
-1 - Migrate from dynet to pytorch
#34
amrsharaf
closed
6 years ago
0
7 - Support pointer networks
#33
amrsharaf
opened
6 years ago
0
6 - Support Precomputed Features
#32
amrsharaf
opened
6 years ago
0
5 - Support Reward Per time-step
#31
amrsharaf
opened
6 years ago
0
4 - Add check for policy steps
#30
amrsharaf
opened
6 years ago
0
3 - Refactor Policy Class
#29
amrsharaf
opened
6 years ago
1
2 - Stateful Learner
#28
amrsharaf
closed
6 years ago
0
1 - Fix nastiness of variable storage in Env
#27
amrsharaf
closed
6 years ago
0
0 - Introduce unit tests
#26
amrsharaf
opened
6 years ago
1
loss function offset and TransitionBOW for cartpole
#25
amrsharaf
closed
6 years ago
0
Different Variants of Hamming Loss
#24
amrsharaf
closed
6 years ago
0
Proximal Policy Optimization Agent
#23
amrsharaf
closed
6 years ago
0
Cart pole envinroment
#22
amrsharaf
closed
6 years ago
0
Mountain Car Environment
#21
amrsharaf
closed
6 years ago
0
Bootstrap Exploration
#20
amrsharaf
closed
6 years ago
2
Support dropout
#19
timvieira
opened
7 years ago
0
policy steps need to be explicit, and history/actions should be a list
#18
hal3
opened
7 years ago
0
Suppprt for dynamic programming modules?
#17
timvieira
opened
7 years ago
0
Experiment with "environment noising" for improving generalization
#16
timvieira
opened
7 years ago
0
Fixed randomness in roll-ins to be able to revisit states in (non-bandit) LOLS
#15
timvieira
opened
7 years ago
2
Implement plain LOLS/AggreVaTe
#14
hal3
closed
7 years ago
1
rename macarico.LearningAlg -> macarico.Learner ?
#13
hal3
closed
7 years ago
1
move stuff out of __init__
#12
hal3
opened
7 years ago
0
How to support batching (for efficiency)?
#11
timvieira
opened
7 years ago
1
Support nondeterministic ref
#10
timvieira
opened
7 years ago
0
seq2seq
#9
timvieira
opened
7 years ago
2
Dependency parsing
#8
timvieira
closed
7 years ago
1
Implement generic "focus" mechanism for neural models
#7
timvieira
closed
7 years ago
0
Implement BanditLOLS
#6
timvieira
opened
7 years ago
2
Create a test harness
#5
timvieira
opened
7 years ago
0
Implement REINFORCE
#4
timvieira
closed
7 years ago
0
Why is this called InverseSigmoidAnnealing?
#3
timvieira
closed
7 years ago
3
Test cases
#2
timvieira
closed
7 years ago
2
Package structure
#1
timvieira
closed
7 years ago
1