devsisters/DQN-tensorflow
Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning
PythonMIT
Issues
- 1
- 1
Ram consumption
#67 opened by anirbanchowdhury9862 - 1
- 3
- 3
- 3
load failed
#64 opened by xiaoxianSun - 0
How to play the code?
#65 opened by NeighborhoodCoding - 7
Error! TimeLimit' object has no attribute 'ale'
#29 opened by tangyudi - 3
- 2
How to run on Windows?
#57 opened by hamiltonwei - 3
Any one who can share model details?
#61 opened by Richardxxxxxxx - 1
terminal in agent.py seem not handle properly
#60 opened by martin6336 - 2
History is not updated with new game screen created after a terminal state is reached
#48 opened by hipoglucido - 1
about starting a new game and History
#59 opened by Richardxxxxxxx - 0
- 5
Help!Why the screen outputs images flow of such low quality as well as with no color?
#35 opened by xihangalpha - 0
why the content is not match the readerme?
#56 opened by zf853109035 - 0
clipped error function is not correct
#55 opened by benjamin-dupuis - 1
CUDA_ERROR_OUT_OF_MEMOR
#49 opened by vulgatecnn - 4
KeyError: '__flags'
#50 opened by jdmartin86 - 1
error memory
#52 opened by damienlancry - 0
No updates to the learning rate
#53 opened by samre12 - 1
Trouble loading checkpoints
#46 opened by xoffey - 1
How to run for more epochs
#47 opened by sbarratt - 1
Name "reduce" is not defined
#45 opened by Unicoranium - 2
Add requirements.txt or alternative
#44 opened by filipre - 12
GPU Utilization
#21 opened by ch3njust1n - 0
README points to deleted paper
#43 opened by filipre - 0
Possible bug of using numpy randint
#42 opened by bigvzhang - 0
Unable to load GPU-trained model
#40 opened by tailintalent - 1
Python 3.x compatibility issues
#38 opened by b0b3rt - 0
- 4
- 2
Rendering error
#22 opened by SavvaI - 2
git checkout fails on Windows 10
#32 opened by krikru - 8
Slower than deep_q_rl
#24 opened by LinZichuan - 6
A bug in the implementation
#16 opened by karpathy - 2
- 0
- 0
- 2
can not reproduce experiment shown in figure
#17 opened by zcyang - 3
Agent.learning_rate is never set?
#28 opened by halflings - 6
Error after 50,000 iterations with Alien-v0 environment running on my MacOS Sierra
#10 opened by shyamalschandra - 2
How to generalize to other Atari Games?
#20 opened by Chia-Hsuan-Lee - 1
Why set terminal=True when live decreases?
#13 opened by LinZichuan - 1
Visualizing the trained data
#18 opened by jlimism - 1
No module named 'utils
#19 opened by Dahandla - 1
model M2 missing in config
#15 opened by zcyang - 0
[!] Load FAILED error
#14 opened by SumbeeLei - 0
Unable to see various charts in Tensorboard Events
#12 opened by bsuper