Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of stoix

stoix - v0.0.2

What's Changed

  • fix: clip mpo actions used in q function to avoid extrapolation by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/55
  • chore: remove self-implemented code in favour of jumanji wrapper by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/56
  • fix: use of truncation in GAE calc by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/57
  • fix: add option to use GAE as value targets by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/58
  • feat: add running statistics utils modified from acme by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/60
  • feat: add beta distribution policy head by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/63
  • Chore/refactor loss metrics by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/61
  • Feat/add ppo penalty by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/64
  • chore: slight change to configs by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/65
  • chore: Make Update Batch Size not affect num envs, buffer size and batch size by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/68
  • fix: double critic being initialised to same network by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/73
  • Chore/refactor type by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/74
  • Feat/add vmpo by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/75
  • fix: recurrent ppo by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/76
  • Chore/change mpo loss by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/80
  • feat: add notebook to plot stoix algorithms by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/87
  • chore: edit readme by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/88
  • feat: add a weights and biases logger by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/89
  • fix: add nstep transitions to d4pg by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/92
  • Feat/rainbow by @RPegoud in https://github.com/EdanToledo/Stoix/pull/86
  • Chore/change muzero networks by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/93
  • chore: move input of distributional network args into config by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/94
  • chore: edit wrappers to have a separate flatten obs wrapper by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/95
  • feat: generalise win rate to be solve rate by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/96
  • Feat/add popjym by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/97
  • fix: typing issues causing double compilation by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/100
  • Feat/add navix by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/101
  • Feat/Add Sebulba by @EdanToledo in https://github.com/EdanToledo/Stoix/pull/105

New Contributors

  • @RPegoud made their first contribution in https://github.com/EdanToledo/Stoix/pull/86

Full Changelog: https://github.com/EdanToledo/Stoix/compare/v0.0.1...v0.0.2

- Python
Published by EdanToledo over 1 year ago

stoix - v0.0.1

First release.

- Python
Published by EdanToledo almost 2 years ago