germain-hug/Deep-RL-Keras
Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)
Python
Issues
- 0
DQN: batch_shape = (None,) + tuple(shape) TypeError: 'int' object is not iterable
#34 opened by Nazanin-87 - 11
- 0
A2C optimizer get_updaet
#33 opened by choasLC - 4
A3C: Issue with keras.function in optimizer
#22 opened by AlconDivino - 2
Unable to run examples
#30 opened by iirekm - 0
A2C can't run NoFrameskip-v4?
#32 opened by THSWind - 4
Can not run DDQN with PER
#21 opened by Xiaoyu006 - 0
Axes don't match array
#31 opened by DalalAbadi - 0
- 2
- 0
- 0
Why we still need to define the action space
#23 opened by YingxiaoKong - 3
Mistake in prioritised replay?
#4 opened by Khev - 0
requirements
#20 opened by constantinserediuc - 0
- 0
MsPacman-v0?
#18 opened by WorksWellWithOthers - 0
Visualizing learning of DDPG with tensorboard
#17 opened by fccoelho - 1
Quick question about DDPG
#16 opened by fccoelho - 0
DDPG - LunarLanderContinuous
#15 opened by cevans3098 - 2
- 3
ResourceExhaustedError
#12 opened by OversightAI - 1
Testing A3C
#13 opened by ndeshp2s - 9
A3C issues
#9 opened by jarlva - 2
- 1
- 2
Save/Load/resume training?
#10 opened by jarlva - 1
Trouble with A3C and Breakout
#7 opened by ChristophePRAT - 2
Q-value updating problem in DDQN
#6 opened by eric-liuyd - 2
Actor update equation in DDPG
#5 opened - 4
Question about A2C
#1 opened by Khev - 2
[Error] Fetch data for Adam
#3 opened