Code

Feature Implement QLearner#144

Code

Merged

usaito merged 10 commits intomasterst-tech/zr-obp:masterfrom

feature/q-learningst-tech/zr-obp:feature/q-learningCopy head branch name to clipboard

Nov 11, 2021

Commits

Commits on Oct 26, 2021

• add q-learner

  usaito

  committed
  240a6ff

  Copy full SHA for 240a6ff

• add tests

  usaito

  committed
  adf796c

  Copy full SHA for adf796c

• unify some test funcs

  usaito

  committed
  fdd4ca2

  Copy full SHA for fdd4ca2

• fix circular import error

  usaito

  committed
  7aca078

  Copy full SHA for 7aca078

• fix numpy warnings

  usaito

  committed
  7d2dab2

  Copy full SHA for 7d2dab2

Commits on Oct 30, 2021

• implement the gumble softmax trick to sample rankings of actions

  usaito

  committed
  d5d1070

  Copy full SHA for d5d1070

Commits on Nov 1, 2021

• fix runtime warnings

  usaito

  committed
  9e5234c

  Copy full SHA for 9e5234c

Commits on Nov 2, 2021

• fix docs

  usaito

  committed
  1d6351b

  Copy full SHA for 1d6351b

• fix warnings

  usaito

  committed
  b0851b1

  Copy full SHA for b0851b1

Commits on Nov 11, 2021

• fix typos

  usaito

  committed
  0583583

  Copy full SHA for 0583583