Ecosyste.ms: Issues

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

GitHub / mobeets/q-rnn issues and pull requests

#22 - move to policy gradient approach?

Issue - State: open - Opened by mobeets 9 months ago - 2 comments

#22 - move to policy gradient approach?

Issue - State: open - Opened by mobeets 9 months ago - 2 comments

#21 - do not encode prev null action

Issue - State: open - Opened by mobeets 9 months ago

#21 - do not encode prev null action

Issue - State: open - Opened by mobeets 9 months ago

#20 - Beron with KL penalty

Issue - State: open - Opened by mobeets 10 months ago - 7 comments

#20 - Beron with KL penalty

Issue - State: open - Opened by mobeets 10 months ago - 7 comments

#19 - Beron DA results

Issue - State: open - Opened by mobeets 10 months ago - 2 comments

#19 - Beron DA results

Issue - State: open - Opened by mobeets 10 months ago - 2 comments

#18 - Beron summary

Issue - State: open - Opened by mobeets 10 months ago - 4 comments

#18 - Beron summary

Issue - State: open - Opened by mobeets 10 months ago - 4 comments

#17 - rllib/catch task: custom evaluation

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

#17 - rllib/catch task: custom evaluation

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

#16 - rllib: make GRU version of use_lstm

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

#16 - rllib: make GRU version of use_lstm

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

#15 - delayed stateless cartpole

Issue - State: closed - Opened by mobeets over 1 year ago - 5 comments

#15 - delayed stateless cartpole

Issue - State: closed - Opened by mobeets over 1 year ago - 5 comments

#14 - Beron _sample_reward bug

Issue - State: closed - Opened by mobeets over 1 year ago
Labels: bug

#14 - Beron _sample_reward bug

Issue - State: closed - Opened by mobeets over 1 year ago
Labels: bug

#13 - R2D2 using Ray

Issue - State: closed - Opened by mobeets over 1 year ago - 1 comment

#13 - R2D2 using Ray

Issue - State: closed - Opened by mobeets over 1 year ago - 1 comment

#12 - Beron2022 timestep level

Issue - State: closed - Opened by mobeets over 1 year ago - 2 comments

#12 - Beron2022 timestep level

Issue - State: closed - Opened by mobeets over 1 year ago - 2 comments

#11 - Beron2022 reparameterization

Issue - State: closed - Opened by mobeets over 1 year ago - 7 comments

#11 - Beron2022 reparameterization

Issue - State: closed - Opened by mobeets over 1 year ago - 7 comments

#10 - Why does Beron2022 have 4 fixed points?

Issue - State: closed - Opened by mobeets over 1 year ago - 6 comments

#10 - Why does Beron2022 have 4 fixed points?

Issue - State: closed - Opened by mobeets over 1 year ago - 6 comments

#9 - Signatures of other Beron2022 models

Issue - State: closed - Opened by mobeets over 1 year ago

#9 - Signatures of other Beron2022 models

Issue - State: closed - Opened by mobeets over 1 year ago

#8 - Beron2022 stickiness

Issue - State: closed - Opened by mobeets over 1 year ago - 5 comments

#7 - Beron2022 stochasticity

Issue - State: closed - Opened by mobeets over 1 year ago - 1 comment

#6 - Beron2022 fixed points

Issue - State: closed - Opened by mobeets over 1 year ago - 3 comments

#5 - Beron2022 working example

Issue - State: closed - Opened by mobeets over 1 year ago - 1 comment

#4 - confirm belief update

Issue - State: closed - Opened by mobeets over 1 year ago

#3 - simpler task?

Issue - State: closed - Opened by mobeets over 1 year ago

#2 - todo: add previous action as a model input (onehot)

Issue - State: closed - Opened by mobeets over 1 year ago

#1 - does the Q function relate to beliefs?

Issue - State: closed - Opened by mobeets over 1 year ago