keon/deep-q-learning issues and pull requests

#37 - Not learning

Issue - State: open - Opened by PietroArsi over 1 year ago

#36 - ValueError: cannot reshape array of size 2 into shape (1,4)

Issue - State: open - Opened by akshay-paranjape about 2 years ago - 2 comments

#35 - Possible incrrection in DQN & DDQN file

Issue - State: open - Opened by YwEwanHuang almost 4 years ago

#34 - Question: Is this some form of reward engineering?

Issue - State: open - Opened by WorksWellWithOthers almost 4 years ago - 1 comment

#33 - Added Dueling Double DQN without PER

Pull Request - State: open - Opened by WorksWellWithOthers almost 4 years ago

#32 - weicc: save data from the Actor

Pull Request - State: closed - Opened by LexieeWei about 4 years ago

#31 - Why are we training the neural network for only 1 epoch

Issue - State: open - Opened by daysofthunder98 over 4 years ago - 1 comment

#30 - Update ddqn.py

Pull Request - State: open - Opened by tfzee almost 5 years ago

#29 - rename methods

Pull Request - State: closed - Opened by keon almost 5 years ago

#28 - slower on GPU using tensorflow backend?

Issue - State: open - Opened by rayset about 5 years ago - 1 comment

#27 - Update ddqn.py

Pull Request - State: closed - Opened by kongrongx over 5 years ago

#26 - IndexError

Issue - State: closed - Opened by aurelieJin over 5 years ago

#25 - Predict the action for new environment - Inference

Issue - State: open - Opened by kk2491 over 5 years ago - 1 comment

#24 - Add files via upload

Pull Request - State: closed - Opened by Xackurai over 5 years ago

#23 - Would it make sense to restrict the action to what's possible?

Issue - State: open - Opened by shamoons over 5 years ago - 2 comments

#22 - ddqn_batch

Issue - State: open - Opened by Sajjad-moghadam over 5 years ago

#21 - What is the purpose of "done"?

Issue - State: closed - Opened by shamoons over 5 years ago - 2 comments

#20 - k frame

Issue - State: open - Opened by fi000 about 6 years ago

#19 - Batch updates and huber loss def

Pull Request - State: closed - Opened by pskrunner14 about 6 years ago - 3 comments

#18 - Speeding the replay

Issue - State: closed - Opened by marxav over 6 years ago - 2 comments

#17 - should update the weight every time step ?

Issue - State: open - Opened by fi000 over 6 years ago - 3 comments

#16 - model save and load does not work

Issue - State: open - Opened by adibyte95 over 6 years ago - 8 comments

#15 - Saving/reloading weight does not seem to work

Issue - State: open - Opened by sbaro over 6 years ago - 2 comments

#14 - memory for state

Issue - State: open - Opened by fi000 over 6 years ago - 4 comments

#13 - missing the initialization of target action value and refreshing the Qhat

Issue - State: open - Opened by fi000 over 6 years ago - 1 comment

#12 - a hidden bug in your code

Issue - State: closed - Opened by haoran-zhang over 6 years ago - 3 comments

#11 - What am I doing wrong?

Issue - State: closed - Opened by mvrozanti about 7 years ago - 2 comments

#10 - fix the value of target[0][action] line 65

Pull Request - State: closed - Opened by tonegas about 7 years ago - 1 comment

#9 - Plot Image

Issue - State: closed - Opened by davsuacar about 7 years ago - 2 comments

#8 - Making new predictions

Issue - State: open - Opened by slakkur1 over 7 years ago - 2 comments

#7 - Update saved models

Pull Request - State: closed - Opened by shibedoge over 7 years ago

#6 - Fixed indentation

Pull Request - State: closed - Opened by kenfehling over 7 years ago - 3 comments

#5 - Added requirements.txt file

Pull Request - State: closed - Opened by RaphaelMeudec over 7 years ago

#4 - add cnn to dqn

Issue - State: closed - Opened by skyer9 over 7 years ago - 3 comments

#3 - fix linter warnning.

Pull Request - State: closed - Opened by skyer9 over 7 years ago

#2 - apply Keras 2 API change.

Pull Request - State: closed - Opened by skyer9 over 7 years ago - 1 comment

#1 - Minor issue with globally scoped variable `env`

Issue - State: closed - Opened by timvieira almost 8 years ago

Ecosyste.ms: Issues

GitHub / keon/deep-q-learning issues and pull requests