Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / hunkim/reinforcementzerotoall issues and pull requests

#26 - Bug?

Issue - State: open - Opened by hccho2 over 4 years ago

#25 - 08_4_softmax_pg_pong_y.py ---> model restore BUG

Issue - State: open - Opened by hccho2 over 4 years ago

#24 - 08_4_softmax_pg_pong.py 에서 image reshape에 관한 질문

Issue - State: open - Opened by hccho2 over 4 years ago

#23 - the PowerPoint

Issue - State: open - Opened by Aleczhang13 about 6 years ago - 1 comment

#22 - Update 10_1_Actor_Critic.ipynb

Pull Request - State: closed - Opened by jerry4897 over 6 years ago - 1 comment

#21 - refactor: DQN docstring & fix divergence

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

#20 - refact: README

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

#18 - add: simple A3C implementations

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

#17 - add: another pong example

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

#16 - log 0 -> nan problem

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

#15 - NP.VSTACK -> List

Pull Request - State: closed - Opened by jinyul80 over 7 years ago - 4 comments

#14 - preventing Nan error with adding epsilon(0.00000001) trick

Pull Request - State: closed - Opened by imcomking over 7 years ago - 12 comments

#13 - code

Pull Request - State: open - Opened by 404akhan over 7 years ago - 2 comments

#12 - MLP --> CNN replaced

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

#11 - add: basic actor-critic network (A2C)

Pull Request - State: closed - Opened by kkweon over 7 years ago - 2 comments

#10 - feat: Cross entropy method

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

#9 - feat: Gym uploader

Pull Request - State: closed - Opened by kkweon over 7 years ago - 2 comments

#8 - fix: DQN

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

#7 - add: test codes

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

#6 - DQN implementations should be updated

Issue - State: closed - Opened by kkweon over 7 years ago

#5 - add: reward normalization

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

#4 - fix: discount reward

Pull Request - State: closed - Opened by kkweon over 7 years ago - 2 comments

#3 - Increase _max_episode_steps in OpenAI Gym CartPole example codes

Pull Request - State: closed - Opened by hyunjun529 over 7 years ago - 2 comments

#2 - using logistic regression cost function

Pull Request - State: closed - Opened by zeran4 over 7 years ago - 4 comments

#1 - Need to Improve Discounted Reward

Issue - State: closed - Opened by kkweon over 7 years ago - 5 comments