awjuliani/DeepRL-Agents
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
Jupyter NotebookMIT
Issues
- 1
_
#60 opened by hassaanhashmi - 1
- 0
Crash and burn in TF 2.0 and alter
#83 opened by lvwarren - 0
Issue in DRQN
#82 opened by p201601 - 0
A garbage code in Model-Network.ipynb
#81 opened by hccho2 - 0
- 2
- 1
- 0
Reward Smoothing
#77 opened by WangChen100 - 0
DRQN plays FlappyBird
#72 opened by WangChen100 - 0
A3C Doom: Why there should be no more workers than there are threads on CPU?
#78 opened by ZhanPython - 0
what is the mean of multiply (1./(i+1))?
#76 opened by law52525 - 1
A possible typo?
#52 opened by XBLDev - 0
A3C Doom : function error
#71 opened by wlghks999 - 0
Please add more comments..
#69 opened by ahmetavc - 0
- 0
apply_gradients need a lock?
#67 opened by michelliming - 0
checkGoal() in gridworld.py
#66 opened by anjany - 2
Can't see the source code.
#64 opened by michelliming - 2
simple and odd python problem
#61 opened by paulsimvient - 0
Double-Dueling-DQN stops learning
#63 opened by florath - 0
- 21
Adapting A3C LSTM for Pong
#48 opened by MatheusMRFM - 0
A3C Doom: Typo in comment
#59 opened by choinker - 2
- 8
Fails to learn
#41 opened by KeirSimmons - 0
Warning Converting sparse IndexedSlices to a dense Tensor of unknown shape on Vanila Policy example
#55 opened by akblissweb - 1
A3C Basic Doom: effect of gamma (Discuss)
#22 opened by IbrahimSobh - 3
DQN python3
#33 opened by ivan-v-kush - 1
A3C Doom Basic: Skip Count
#30 opened by IbrahimSobh - 1
A3C Doom: execute agent
#51 opened by drsagitn - 0
A3C-Doom w MultiRNNCell?
#50 opened by lefnire - 0
A3C episode length unbounded
#49 opened by mkisantal - 1
- 3
- 0
Simple Policy Faulty Loss Function
#45 opened by wert23239 - 1
A3C Basic Doom: Loss Function
#21 opened by IbrahimSobh - 0
When I run dueling DQN, there is an error, 'The kernel appears to have died. It will restart automatically.'.
#40 opened by wonchul-kim - 2
invalid value encountered in less
#27 opened by DMTSource - 0
Learning rates and initial random weights
#39 opened by IbrahimSobh - 0
Low Rewards for DRQN
#38 opened by yenlianglintw - 3
- 0
A3C Doom: Visualize Gradients (tricky)
#36 opened by IbrahimSobh - 0
Solving NaN vlaues
#34 opened by IbrahimSobh - 2
What is `grad_norms` in AC_Network?
#29 opened by yrlu - 3
# For Policy Network Problem
#28 opened by cumttang - 4
- 5
- 0
Environment
#24 opened by Kyxsune - 0