Code

Feature policy learner#132

Code

Merged

usaito merged 16 commits intomasterst-tech/zr-obp:masterfrom

feature-policy-learnerst-tech/zr-obp:feature-policy-learnerCopy head branch name to clipboard

Sep 6, 2021

Commits

Commits on Sep 4, 2021

• exclude OPEEstimator from NNPolicyLearner

  usaito

  committed
  8802665

  Copy full SHA for 8802665

• add Adagrad

  usaito

  committed
  2158a28

  Copy full SHA for 2158a28

• rm estimate_policy_value_tensor from OPEEstimator as it is no longer necessary

  usaito

  committed
  1760002

  Copy full SHA for 1760002

• add isort

  usaito

  committed
  0aeff65

  Copy full SHA for 0aeff65

• adjust to the update in obp and apply isort

  usaito

  committed
  f9a556e

  Copy full SHA for f9a556e

• apply isort

  usaito

  committed
  6eeffcd

  Copy full SHA for 6eeffcd

• fix lint

  usaito

  committed
  8943385

  Copy full SHA for 8943385

• modify defaults and fix bugs

  usaito

  committed
  4ed27ed

  Copy full SHA for 4ed27ed

• apply black

  usaito

  committed
  76ad4b6

  Copy full SHA for 76ad4b6

• fix config

  usaito

  committed
  b6e53e7

  Copy full SHA for b6e53e7

• fix a failed test

  usaito

  committed
  23f03a8

  Copy full SHA for 23f03a8

Commits on Sep 5, 2021

• bug fix

  usaito

  committed
  e3e43d0

  Copy full SHA for e3e43d0

• resolve conflict

  usaito

  committed
  e1340f0

  Copy full SHA for e1340f0

• adjust to updates

  usaito

  committed
  95f760a

  Copy full SHA for 95f760a

Commits on Sep 6, 2021

• resolve

  usaito

  committed
  9cf1e64

  Copy full SHA for 9cf1e64

• update quickstart examples

  usaito

  committed
  f7a6a28

  Copy full SHA for f7a6a28