issues
search
hunkim
/
ReinforcementZeroToAll
249
stars
132
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Bug?
#26
hccho2
opened
4 years ago
0
08_4_softmax_pg_pong_y.py ---> model restore BUG
#25
hccho2
opened
4 years ago
0
08_4_softmax_pg_pong.py 에서 image reshape에 관한 질문
#24
hccho2
opened
4 years ago
0
the PowerPoint
#23
Aleczhang13
opened
6 years ago
1
Update 10_1_Actor_Critic.ipynb
#22
jerry4897
closed
6 years ago
1
refactor: DQN docstring & fix divergence
#21
kkweon
closed
7 years ago
0
refact: README
#20
kkweon
closed
7 years ago
0
10_1_Actor_Critic.ipynb 에 관한 질문입니다! (Question about 10_1 Actor_Critic)
#19
wonchul-kim
closed
7 years ago
4
add: simple A3C implementations
#18
kkweon
closed
7 years ago
0
add: another pong example
#17
kkweon
closed
7 years ago
0
log 0 -> nan problem
#16
imcomking
closed
7 years ago
0
NP.VSTACK -> List
#15
jinyul80
closed
7 years ago
4
preventing Nan error with adding epsilon(0.00000001) trick
#14
imcomking
closed
7 years ago
12
code
#13
404akhan
opened
7 years ago
2
MLP --> CNN replaced
#12
imcomking
closed
7 years ago
1
add: basic actor-critic network (A2C)
#11
kkweon
closed
7 years ago
2
feat: Cross entropy method
#10
kkweon
closed
7 years ago
0
feat: Gym uploader
#9
kkweon
closed
7 years ago
2
fix: DQN
#8
kkweon
closed
7 years ago
1
add: test codes
#7
kkweon
closed
7 years ago
1
DQN implementations should be updated
#6
kkweon
closed
7 years ago
0
add: reward normalization
#5
kkweon
closed
7 years ago
0
fix: discount reward
#4
kkweon
closed
7 years ago
2
Increase _max_episode_steps in OpenAI Gym CartPole example codes
#3
hyunjun529
closed
7 years ago
2
using logistic regression cost function
#2
zeran4
closed
7 years ago
4
Need to Improve Discounted Reward
#1
kkweon
closed
7 years ago
5