Farama-Foundation/Shimmy

📦 Shimmy 1.3.0 Release Notes:

• This release updates Shimmy's Melting Pot wrapper to use Melting Pot's [pypi release](https://pypi.org/project/dm-meltingpot/), and includes a minor rendering bugfix for dm_control,
• Note: Melting Pot requires python version >= 3.10, please upgrade your python installation if you intend to use this wrapper

💥 Breaking Changes

• `install_melting_pot.sh` has been removed, as it is no longer necessary for installation because we are using Melting Pot's pypi release
• To install all required dependencies, simply run `pip install shimmy[meltingpot]`

✨ New Features and Improvements

• Update Melting Pot wrapper to use pypi release (https://github.com/Farama-Foundation/Shimmy/pull/111)

🐛 Bug Fixes

• Fix dm_control rendering bug when human mode is used by (https://github.com/Farama-Foundation/Shimmy/pull/104)

📦 Contributors

• @elliottower, @pseudo-rnd-thoughts, @spiglerg @KaleabTessera
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v1.2.1...v1.3.0

📦 Shimmy 1.2.1 Release Notes:

• This is a minor hotfix which solves an issue where the Melting Pot dockerfile was not running successfully, leading to CI failures and making our install scripts fail.

🐛 Bug Fixes

• Fix meltingpot dockerfile (https://github.com/Farama-Foundation/Shimmy/pull/102)
• Fix meltingpot install script (https://github.com/Farama-Foundation/Shimmy/pull/103)
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v1.2.0...v1.2.1

💥 Breaking Changes

• Python 3.7 has reached its end of life support ([link](https://endoflife.date/python)), therefore, we have dropped support for it in favor of 3.11.
• Observation spaces and action spaces in OpenSpiel wrapper are now indexed by agent name, rather than agent ID, to match PettingZoo
• This brings the wrapper to fully match PettingZoo's environment format, enabling easier usage with wrappers and external training libraries

✨ New Features and Improvements

• Python 3.11 support has been added (https://github.com/Farama-Foundation/Shimmy/pull/100)
• Update pre-commit config to match Gymnasium (https://github.com/Farama-Foundation/Shimmy/pull/99)
• CI now ensures proper formatting for toml and yml files, checks that shell scripts have shebangs and can be executed, etc.

🐛 Bug Fixes

• OpenSpiel wrapper: fix obs/action space, seeding, and reset config (https://github.com/Farama-Foundation/Shimmy/pull/96)
• OpenSpiel wrapper: fix calling reset() with no seed, make obs/act spaces fully match PettingZoo (https://github.com/Farama-Foundation/Shimmy/pull/97)

📝 Documentation Updates

• Add badges: pre-commit, black, DOI badge from Zenodo (https://github.com/Farama-Foundation/Shimmy/pull/95)
• Fix documentation for installing multiple extras to be correct syntax (https://github.com/Farama-Foundation/Shimmy/pull/93)
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v1.1.0...v1.2.0

📦 **Shimmy 1.1.0 Release Notes:**

• This is a small bug fix release which fixes rendering issues in the dm-control compatibility wrapper.

💥 Breaking changes

• The dm-control compatibility environment used the `env.control_timesteps()` for the render frames per second (`render_fps`), however, this value is the interval between actions per seconds, i.e., `0.04`. This was fixed to be the actual `fps`, by multiplying by 1000. (https://github.com/Farama-Foundation/Shimmy/pull/91)
• A `dt` attribute was added to the dm-control compatibility environment that is equivalent to the mujoco environment `dt` attribute. (https://github.com/Farama-Foundation/Shimmy/pull/91)
• Modified the rendering in dm-control compatibility, removing `render_height`, `render_width`, `camera_id` and `scene_callback` in favor of `render_kwargs`. (https://github.com/Farama-Foundation/Shimmy/pull/92)
• As such users should specify kwargs in the dm-control engine render function, i.e., `height`, `width`, `camera_id` and `scene_callback`.
• Additionally, this will use the default dm-control arguments unless overridden by the user `render_kwargs`.
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v1.0.1...v1.1.0

🐛 **Bug Fixes**

• Update DM control multi agent and melting pot to PettingZoo 1.23.0 API, fix seeding (https://github.com/Farama-Foundation/Shimmy/pull/87)
• Update OpenSpiel to PettingZoo 1.23.0 API, fix API test & seeding (https://github.com/Farama-Foundation/Shimmy/pull/80)
• Fix setup.py for gym v21 (https://github.com/Farama-Foundation/Shimmy/pull/88)

📝 **Documentation Updates**

• Allow users to view source code of referenced objects on the website (https://github.com/Farama-Foundation/Shimmy/pull/78)
• Add text logo to homepage, matching other Farama sites (https://github.com/Farama-Foundation/Shimmy/pull/79)
• Fix homepage mobile images being squished (https://github.com/Farama-Foundation/Shimmy/pull/81)
• Fix typo on homepage image grid (https://github.com/Farama-Foundation/Shimmy/pull/86)
• Create CITATION.cff to allow easier citation of the repository (https://github.com/Farama-Foundation/Shimmy/pull/83)
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v1.0.0...v1.0.1

📦 Single-agent (Gymnasium wrappers):

• [Arcade Learning Environments](https://github.com/mgbellemare/Arcade-Learning-Environment)
• [DeepMind Behavior Suite](https://shimmy.farama.org/contents/bsuite/)
• [DeepMind Control](https://github.com/deepmind/dm_control/)
• [DeepMind Lab](https://github.com/deepmind/lab)
• [OpenAI Gym](https://github.com/openai/gym) - [V21](https://github.com/openai/gym/releases/tag/v0.21.0)
• [OpenAI Gym](https://github.com/openai/gym) - [V26](https://github.com/openai/gym/releases/tag/0.26.0) (breaking API change)

📦 Multi-agent (PettingZoo wrappers):

• [DeepMind OpenSpiel](https://github.com/deepmind/open_spiel)
• [DeepMind Control: Soccer](https://github.com/deepmind/dm_control/blob/main/dm_control/locomotion/soccer/README.md)
• [DeepMind Melting Pot](https://github.com/deepmind/meltingpot)
• Single-agent environments can be easily loaded using Gymnasium’s [registry ](https://gymnasium.farama.org/api/registry/)and `make()` function as follows:
• ```python
• import gymnasium as gym
• env = gym.make("dm_control/acrobot-swingup_sparse-v0", render_mode="human")
• ```
• + 5 more

💥 Breaking Changes

• `OpenspielCompatibilityV0` has been renamed to `OpenSpielCompatibilityV0` (correct spelling of [OpenSpiel](https://github.com/deepmind/open_spiel))
• Since the v0.21.0 release, the `setup.py` has been updated to include separate install options for gym V21 and V26:
• Instead of `pip install shimmy[gym]`, you must select either: `pip install shimmy[gym-v21]` or `pip install shimmy[gym-v26]`

✨ New Features and Improvements

• This release adds support for three additional environments:
• [DeepMind Lab](https://github.com/deepmind/lab) (single-agent)
• [DeepMind Behavior Suite](https://shimmy.farama.org/contents/bsuite/) (single-agent)
• [DeepMind Melting Pot](https://github.com/deepmind/meltingpot) (multi-agent)
• [/scripts/install_dm_lab.sh](https://github.com/Farama-Foundation/Shimmy/blob/main/scripts/install_dm_lab.sh)
• [/scripts/install_melting_pot.sh](https://github.com/Farama-Foundation/Shimmy/blob/main/scripts/install_melting_pot.sh)

🐛 Bug Fixes and Documentation Updates

• Full example usage scripts are now provided for each environment, allowing users to easily load and interact with an environment without prior knowledge.
• Example: run a `dm-control` environment:
• ```python
• observation, info = env.reset(seed=42)
• for _ in range(1000):
• action = env.action_space.sample() # this is where you would insert your policy
• observation, reward, terminated, truncated, info = env.step(action)
• if terminated or truncated:
• + 4 more

🐛 Bug Fixes

• Fixed dm-control step termination and truncation, previously this was the opposite of the specification by @pseudo-rnd-thoughts and @ottofabianin in https://github.com/Farama-Foundation/Shimmy/pull/30
• Check if the default wrappers exist before stripping for compatibility with Gym `v0.21` by @nuance1979 in https://github.com/Farama-Foundation/Shimmy/pull/34
• Update the list of dm-control environments for 1.0.10 to include humanoid-cmu talk by @pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Shimmy/pull/36
• Remove warning that `GymV22Environment` and `GymV26Environment` are overwritten and change `V22` to `V21` in the `GymV22Environment` by @pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Shimmy/pull/29
• Bump ale-py to `v0.8.1` which includes a number of bug fixes by @pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Shimmy/pull/37/. For all the changes, read the [release notes](https://github.com/mgbellemare/Arcade-Learning-Environment/releases/tag/v0.8.1).
• Finally, @jjshoots and @SiddarGu updated the documentation in https://github.com/Farama-Foundation/Shimmy/pull/28 and https://github.com/Farama-Foundation/Shimmy/pull/25 respectively.
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v0.2.0...v0.2.1

📋 Changes

• Add some friendly docs on how to get started by @vwxyzjn in https://github.com/Farama-Foundation/Shimmy/pull/20
• Update gym compatibility environment names by @pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Shimmy/pull/16
• Add dm-lab (no tests yet) and dm-control-multiagent by @jjshoots in https://github.com/Farama-Foundation/Shimmy/pull/7
• Add `__getattr__` to Gym compatibility env to fix atari preprocessing issue, add registration of dm-lab compatibility environment. by @pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Shimmy/pull/22

✨ New Contributors

• @vwxyzjn made their first contribution in https://github.com/Farama-Foundation/Shimmy/pull/20
• Full Changelog: https://github.com/Farama-Foundation/Shimmy/compare/v0.1.0...v0.2.0

📋 Changes

• OpenAI Gym: We provide compatibility environments for V22 and V26 environments, `GymV22Environment-v0` and `GymV26Environment-v0`
• dm-control: suite, manipulation and locomotion (currently the soccer environments are not supported)
• atari: As ale-py had not added gymnasium support yet, shimmy adds the `AtariEnv` with a couple of very minor changes that are backward compatible with the gym environments.
• openspiel: We support a large number of the environments, however not all of them