Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of dm-meltingpot

dm-meltingpot - v2.4.0

Changed

  • Split out subjects and add more checks for VideoSubject
  • Update supported version of opencv

Fixed

  • #246
    • Fix clean_up_20 to use the correct puppet bot
    • Delete territoryrooms_6 as it is a duplicate of territoryrooms_5

- Python
Published by jagapiou about 1 year ago

dm-meltingpot - v2.3.1

Update Melting Pot version to 2.3.1.

Added

  • The results of the Melting Pot Competition, NeurIPS 2023.
  • Updates to the evaluation notebook to use the new results.

- Python
Published by duenez over 1 year ago

dm-meltingpot - v2.3.0

[2.3.0] - 2024-06-27

Added

  • New scenarios, puppets and bots used in the Melting Pot Contest, NeurIPS 2023.

Known issues

  • Two scenarios in the competition were set up wrongly. Tracking issue: https://github.com/google-deepmind/meltingpot/issues/246
    • clean_up_20 is using the wrong (puppet) bot: clean_up__puppet_sanctioning_alternator_nice_0 instead of clean_up__puppet_sanctioning_alternator_0.
    • territory__rooms_6 is identical to territory__rooms_5.

- Python
Published by duenez over 1 year ago

dm-meltingpot - v2.2.2

Fixed

  • Update setup.py to work with earlier setuptools (fixes broken 2.2.1 release).

- Python
Published by jagapiou almost 2 years ago

dm-meltingpot - v2.2.1 [YANKED]

Changed

  • Do not allow orientation = None in Transform objects
  • Improve documentation for territory__*.
  • Improve scenario tags.
  • Move puppeteers testutils to testing dir.
  • remove restriction on chex
  • Update setup.py to work with older versions of setuptools
  • Add dev tools to setup.py
  • Add pytest-xdist as a required plugin.
  • Update pylintrc

Fixed

  • Debug observations break hidden agenda #168
  • Various lint errors

Removed

  • Residual v1 file: reactiongraphutils.py
  • Remove stale documentation left over from 1.0.

- Python
Published by jagapiou almost 2 years ago

dm-meltingpot - v2.2.1

Changed

  • Do not allow orientation = None in Transform objects
  • Improve documentation for territory__*.
  • Improve scenario tags.
  • Move puppeteers testutils to testing dir.
  • remove restriction on chex
  • Update setup.py to work with older versions of setuptools
  • Add dev tools to setup.py
  • Add pytest-xdist as a required plugin.
  • Update pylintrc

Fixed

  • Debug observations that break hidden agenda #168
  • Various lint errors

Removed

  • Residual v1 file: reactiongraphutils.py
  • Remove stale documentation left over from 1.0.

- Python
Published by jagapiou almost 2 years ago

dm-meltingpot - v2.2.0

Changed

  • Make meltingpot pip installable.
  • Support import meltingpot as an alias of import meltingpot.python.
  • Raise minimum Python version to Python 3.10.
  • Install assets as part of pip install .
  • Update Dockerfile and dev tooling (pytest, pyink, pytype, pylint, isort).
  • Update examples to work with v2.
  • Update README.md with new installation details.
  • Migrate from rx to reactivex.

Fixed

  • Remove type annotation for dtype.
  • Use correct roles in playhiddenagenda.
  • Fix noop that was causing a typing error.
  • Add missing __init__.py files.
  • Set the default orientation to NORTH for objects that have no orientation defined.

Added

  • Evaluation utilities.

- Python
Published by jagapiou over 2 years ago

dm-meltingpot - v2.1.1

Changed

  • Added COLLECTIVERETURN to PERMITTEDOBSERVATIONS.
  • Split install.sh into three scripts.
  • Move from yapf to black.
  • Remove debug observations to speed up environment stepping.

Fixed

  • Add Lua 5.2 compatibility for unpack.

Removed

  • SubstrateWrappers previously needed for the v1 bots.

Added

  • Colab for visualizing evaluation results.
  • Tests for the examples.
  • Mocks of specific substrates and scenarios, for use in testing.
  • Helper for setting world.rgb spec.

- Python
Published by jagapiou almost 3 years ago

dm-meltingpot - v2.1.0

Changed

  • Improve debugging information in SavedModelPolicy.
  • Resample bots at the beginning of scenario episodes.

Fixed

  • Initialize Transform before any other component (#84, #24).

Added

  • New substrate "Hidden Agenda" and its scenarios.

- Python
Published by jagapiou about 3 years ago

dm-meltingpot - v2.0.0

Melting Pot Version 2.0.0 release. See Melting Pot 2.0 Tech Report for detailed information on the new substrates, bots, and scenarios.

Changed

  • Removed all v1 scenarios, bots, and substrates and replaced with new versions.
  • Scenarios now support heterogenous roles, which must be specified at build time.
  • Various improvements to examples and their documentation.

Added

  • New puppeteers and policies to implement new bots.
  • New utils to handle sprites, colors, and maps.
  • Mocks for use in testing.

- Python
Published by jagapiou over 3 years ago

dm-meltingpot - v1.0.4

Changed

  • Drop support for Python 3.7 and 3.8.
  • Store saved models on Google Cloud Platform rather than in the Git repo.
  • x2 speed improvement to some substrates
  • Improved install.sh script and installation documentation.
  • Various improvements to examples and their documentation.

Fixed

  • Puppets were sharing state in Scenarios. #70
  • Various issues with RLlib examples.

Added

  • .devcontainer for the project.
  • pettingzoo example.
  • TF1-compatible version of SavedModelPolicy.

- Python
Published by jagapiou over 3 years ago

dm-meltingpot - v1.0.3

Changed

  • Define is_focal is in scenario configs.
  • Use chex.dataclass for dm-tree compatibility.

Fixed

  • Use correct is_focal settings for team-vs-team games #16.

- Python
Published by jagapiou almost 4 years ago

dm-meltingpot - v1.0.2

Added

  • Substrates and Scenarios now have ReactiveX observables.

Changed

  • Don't add INVENTORY observation to scenarios that don't use it.
  • Various updates to RLlib example.
  • Improved performance of the component system for environments.

Fixed

  • Simulation Speed #7
  • Horizon setting in examples #9
  • Error running example "selfplaytrain.py" #10
  • build lab2d on m1 chip #13

Full Changelog: https://github.com/deepmind/meltingpot/commits/v1.0.2

- Python
Published by jagapiou about 4 years ago

dm-meltingpot - v1.0.0

Initial release.

Full Changelog: https://github.com/deepmind/meltingpot/commits/v1.0.0

- Python
Published by jagapiou over 4 years ago

dm-meltingpot - v1.0.1

Submitted a number of fixes to ensure substrates and scenarios operate as intended. Other changes not expected to have any impact.

Fixed: - Python seed is not forwarded to Lua #4 - Second episode using same seed as the first #5 - Bots receive incorrect timesteps in Scenario #3

Full Changelog: https://github.com/deepmind/meltingpot/commits/v1.0.1

- Python
Published by jagapiou over 4 years ago