Gym Release Notes#
0.26.2#
Released on 2022-10-04 - GitHub - PyPI
Release notes
This is another very minor bug release.
Bugs Fixes
- As
reset
now returns(obs, info)
then in the vector environments, this caused the finalstep
's info to be overwritten. Now, the final observation and info are contained within the info as "final_observation" and "final_info" @pseudo-rnd-thoughts - Adds warnings when trying to render without specifying the
render_mode
@younik - Updates Atari Preprocessing such that the wrapper can be pickled @vermouth1992
- Github CI was hardened to such that the CI just has read permissions @sashashura
- Clarify and fix typo in
GraphInstance
@ekalosak
0.26.1#
Released on 2022-09-16 - GitHub - PyPI
Release Notes
This is a very minor bug fix release for 0.26.0
Bug Fixes
- #3072 - Previously
mujoco
was a necessary module even if onlymujoco-py
was used. This has been fixed to allow onlymujoco-py
to be installed and used. @YouJiacheng - #3076 -
PixelObservationWrapper
raises an exception if theenv.render_mode
is not specified. @vmoens - #3080 - Fixed bug in
CarRacing
where the colour of the wheels were not correct @foxik - #3083 - Fixed BipedalWalker where if the agent moved backwards then the rendered arrays would be a different size. @younik
Spelling
0.26.0#
Released on 2022-09-06 - GitHub - PyPI
Release notes for v0.26.0
This release is aimed to be the last of the major API changes to the core API. All of the previously "turned off" changes of the base API (step termination / truncation, reset info, no seed function, render mode determined by initialization) are now expected by default. We still plan to make breaking changes to Gym itself, but to things that are very easy to upgrade (environments and wrappers), and things that aren't super commonly used (the vector API). Once those aspects are stabilized, we'll do a proper 1.0 release and follow semantic versioning. Additionally, unless something goes terribly wrong with this release and we have to release a patched version, this will be the last release of Gym for a while.
If you've been waiting for a "stable" release of Gym to upgrade your project given all the changes that have been going on, this is the one.
We also just wanted to say that we tremendously appreciate the communities patience with us as we've gone on this journey taking over the maintenance of Gym and making all of these huge changes to the core API. We appreciate your patience and support, but hopefully, all the changes from here on out will be much more minor.
Breaking backward compatibility
These changes are true of all gym's internal wrappers and environments but for environments not updated, we provide the EnvCompatibility
wrapper for users to convert old gym v21 / 22 environments to the new core API. This wrapper can be easily applied in gym.make
and gym.register
through the apply_api_compatibility
parameters.
Step
Termination / truncation - TheEnv.step
function returns 5 values instead of 4 previously (observations, reward, termination, truncation, info
). A blog with more details will be released soon to explain this decision. @arjun-kg- Reset info - The
Env.reset
function returns two values (obs
andinfo
) with noreturn_info
parameter for gym wrappers and environments. This is important for some environments that provided action masking information for each actions which was not possible for resets. @balisujohn - No
Seed
function - WhileEnv.seed
was a helpful function, this was almost solely used for the beginning of the episode and is added togym.reset(seed=...)
. In addition, for several environments like Atari that utilise external random number generators, it was not possible to set the seed at any time other thanreset
. Therefore,seed
is no longer expected to function within gym environments and is removed from all gym environments @balisujohn - Rendering - It is normal to only use a single render mode and to help open and close the rendering window, we have changed
Env.render
to not take any arguments and so all render arguments can be part of the environment's constructor i.e.,gym.make("CartPole-v1", render_mode="human")
. For more detail on the new API, see blog post @younik
Major changes
- Render modes - In
v25
, there was a change in the meaning of render modes, i.e. "rgb_array" returned a list of rendered frames with "single_rgb_array" returned a single frame. This has been reverted in this release with "rgb_array" having the same meaning as previously to return a single frame with a new mode "rgb_array_list" returning a list of RGB arrays. The capability to return a list of rendering observations achieved through a wrapper applied duringgym.make
. #3040 @pseudo-rnd-thoughts @younik - Added
save_video
that usesmoviepy
to render a list of RGB frames and updatedRecordVideo
to use this function. This removes support for recordingansi
outputs. #3016 @younik RandomNumberGenerator
functions:rand
,randn
,randint
,get_state
,set_state
,hash_seed
,create_seed
,_bigint_from_bytes
and_int_list_from_bigint
have been removed. @balisujohn- Bump
ale-py
to0.8.0
which is compatibility with the new core API - Added
EnvAPICompatibility
wrapper @RedTachyon
Minor changes
- Added improved
Sequence
,Graph
andText
sample masking @pseudo-rnd-thoughts - Improved the gym
make
andregister
type hinting withentry_point
being a necessary parameter ofregister
. #3041 @pseudo-rnd-thoughts - Changed all URL to the new gym website https://www.gymlibrary.dev/ @FieteO
- Fixed mujoco offscreen rendering with weight and height value > 500 #3044 @YouJiacheng
- Allowed toy_text environment to render on headless machines #3037 @RedTachyon
- Renamed the motors in the mujoco swimmer envs #3036 @lin826
0.25.2#
Released on 2022-08-18 - GitHub - PyPI
Release notes for v0.25.2
This is a fairly minor bug fix release.
Bug Fixes
- Removes requirements for
_TimeLimit.truncated
in info for step compatibility functions. This makes the step compatible with Envpool @arjun-kg - As the ordering of
Dict
spaces matters when flattening spaces, updated the__eq__
to account for the.keys()
ordering. @XuehaiPan - Allows
CarRacing
environment to be pickled. Updated all gym environments to be correctly pickled. @RedTachyon - seeding
Dict
andTuple
spaces with integers can cause lower-specification computers to hang due to requiring 8Gb memory. Updated the seeding with integers to not require unique subseeds (subseed collisions are rare). For users that require unique subseeds for all subspaces, we recommend using a dictionary or tuple with the subseeds. @olipinski - Fixed the metaclass implementation for the new render api to allow custom environments to use metaclasses as well. @YouJiacheng
Updates
- Simplifies the step compatibility functions to make them easier to debug. Time limit wrapper with the old step API favours terminated over truncated if both are true. This is as the old done step API can only encode 3 states (cannot encode
terminated=True
andtruncated=True
) therefore we must encode to onlyterminated=True
ortruncated=True
. @pseudo-rnd-thoughts - Add Swig as a dependency @kir0ul
- Add type annotation for
render_mode
andmetadata
@bkrl
0.25.1#
Released on 2022-07-26 - GitHub - PyPI
Release notes
- Added rendering for CliffWalking environment @younik
PixelObservationWrapper
only supports the new render API due to difficulty in supporting both old and new APIs. A warning is raised if the user is using the old API @vmoens
Bug fix
- Revert an incorrect edition on wrapper.FrameStack @ZhiqingXiao
- Fix reset bounds for mountain car @psc-g
- Removed skipped tests causing bugs not to be caught @pseudo-rnd-thoughts
- Added backward compatibility for environments without metadata @pseudo-rnd-thoughts
- Fixed
BipedalWalker
rendering for RGB arrays @1b15 - Fixed bug in
PixelObsWrapper
for using the new rendering @younik
Typos
- Rephrase observations' definition in Lunar Lander Environment @EvanMath
- Top-docstring in
gym/spaces/dict.py
@Ice1187 - Several typos in
humanoidstandup_v4.py
,mujoco_env.py
, andvector_list_info.py
@timgates42 - Typos in passive environment checker @pseudo-rnd-thoughts
- Typos in Swimmer rotations @lin826
0.25.0#
Released on 2022-07-13 - GitHub - PyPI
Release notes
This release finally introduces all new API changes that have been planned for the past year or more, all of which will be turned on by default in a subsequent release. After this point, Gym development should get massively smoother. This release also fixes large bugs present in 0.24.0 and 0.24.1, and we highly discourage using those releases.
API Changes
Step
- A majority of deep reinforcement learning algorithm implementations are incorrect due to an important difference in theory and practice asdone
is not equivalent totermination
. As a result, we have modified thestep
function to return five values,obs, reward, termination, truncation, info
. The full theoretical and practical reason (along with example code changes) for these changes will be explained in a soon-to-be-released blog post. The aim for the change to be backward compatible (for now), for issues, please put report the issue on github or the discord. @arjun-kgRender
- The render API is changed such that the mode has to be specified duringgym.make
with the keywordrender_mode
, after which, the render mode is fixed. For further details see https://younis.dev/blog/2022/render-api/ and #2671. This has the additional changes- with
render_mode="human"
you don't need to call .render(), rendering will happen automatically onenv.step()
- with
render_mode="rgb_array"
,.render()
pops the list of frames rendered since the last.reset()
- with
render_mode="single_rgb_array"
,.render()
returns a single frame, like before.
- with
Space.sample(mask=...)
allows a mask when sampling actions to enable/disable certain actions from being randomly sampled. We recommend developers add this to theinfo
parameter returned byreset(return_info=True)
andstep
. See #2906 for example implementations of the masks or the individual spaces. We have added an example version of this in the taxi environment. @pseudo-rnd-thoughts- Add
Graph
for environments that use graph style observation or action spaces. Currently, the node and edge spaces can only beBox
orDiscrete
spaces. @jjshoots - Add
Text
space for Reinforcement Learning that involves communication between agents and have dynamic length messages (otherwiseMultiDiscrete
can be used). @ryanrudes @pseudo-rnd-thoughts
Bug fixes
- Fixed car racing termination where if the agent finishes the final lap, then the environment ends through truncation not termination. This added a version bump to Car racing to v2 and removed Car racing discrete in favour of
gym.make("CarRacing-v2", continuous=False)
@araffin - In
v0.24.0
,opencv-python
was an accidental requirement for the project. This has been reverted. @KexianShen @pseudo-rnd-thoughts - Updated
utils.play
such that if the environment specifieskeys_to_action
, the function will automatically use that data. @Markus28 - When rendering the blackjack environment, fixed bug where rendering would change the dealers top car. @balisujohn
- Updated mujoco docstring to reflect changes that were accidently overwritten. @Markus28
Misc
- The whole project is partially type hinted using pyright (none of the project files is ignored by the type hinter). @RedTachyon @pseudo-rnd-thoughts (Future work will add strict type hinting to the core API)
- Action masking added to the taxi environment (no version bump due to being backwards compatible) @pseudo-rnd-thoughts
- The
Box
space shape inference is allowshigh
andlow
scalars to be automatically set to(1,)
shape. Minor changes to identifying scalars. @pseudo-rnd-thoughts - Added option support in classic control environment to modify the bounds on the initial random state of the environment @psc-g
- The
RecordVideo
wrapper is becoming deprecated with no support forTextEncoder
with the new render API. The plan is to replaceRecordVideo
with a single function that will receive a list of frames from an environment and automatically render them as a video usingMoviePy
. @johnMinelli - The gym
py.Dockerfile
is optimised from 2Gb to 1.5Gb through a number of optimisations @TheDen
0.24.1#
Released on 2022-06-07 - GitHub - PyPI
This is a bug fix release for version 0.24.0
Bugs fixed:
- Replaced the environment checker introduced in V24, such that the environment checker will not call
step
andreset
during make. This new version is a wrapper that will observe the data thatstep
andreset
returns on their first call and check the data against the environment checker. @pseudo-rnd-thoughts - Fixed MuJoCo v4 arguments key callback, closing the environment in renderer and the mujoco_rendering close method. @rodrigodelazcano
- Removed redundant warning in registration @RedTachyon
- Removed maths operations from MuJoCo xml files @quagla
- Added support for unpickling legacy
spaces.Box
@pseudo-rnd-thoughts - Fixed mujoco environment action and observation space docstring tables @pseudo-rnd-thoughts
- Disable wrappers from accessing
_np_random
property andnp_random
is now forwarded to environments @pseudo-rnd-thoughts - Rewrite setup.py to add a "testing" meta dependency group @pseudo-rnd-thoughts
- Fixed docstring in
rescale_action
wrapper @gianlucadecola
0.24.0#
Released on 2022-05-25 - GitHub - PyPI
Major changes
- Added v4 mujoco environments that use the new deepmind mujoco 2.2.0 module.
This can be installed throughpip install gym[mujoco]
with the old bindings still being
available using thev3
environments andpip install gym[mujoco-py]
.
These newv4
environment should have the same training curves asv3
. For the Ant, we found that there was a
contact parameter that was not applied inv3
that can enabled inv4
however was found to produce significantly
worse performance see comment for more details. @rodrigodelazcano - The vector environment step
info
API has been changes to allow hardware acceleration in the future.
See this PR for the modifiedinfo
style that now uses dictionaries instead of a list of environment info.
If you still wish to use the list info style, then use theVectorListInfo
wrapper. @gianlucadecola - On
gym.make
, the gymenv_checker
is run that includes calling the environmentreset
andstep
to check if the
environment is compliant to the gym API. To disable this feature, rungym.make(..., disable_env_checker=True)
. @RedTachyon - Re-added
gym.make("MODULE:ENV")
import style that was accidentally removed in v0.22 @arjun-kg Env.render
is now order enforced such thatEnv.reset
is required beforeEnv.render
is called. If this a required
feature then set theOrderEnforcer
wrapperdisable_render_order_enforcing=True
. @pseudo-rnd-thoughts- Added wind and turbulence to the Lunar Lander environment, this is by default turned off,
use thewind_power
andturbulence
parameter. @virgilt - Improved the
play
function to allows multiple keyboard letter to pass instead of ascii value @Markus28 - Added google style pydoc strings for most of the repositories @pseudo-rnd-thoughts @Markus28
- Added discrete car racing environment version through
gym.make("CarRacing-v1", continuous=False)
- Pygame is now an optional module for box2d and classic control environments that is only necessary for rendering.
Therefore, install pygame usingpip install gym[box2d]
orpip install gym[classic_control]
@gianlucadecola @RedTachyon - Fixed bug in batch spaces (used in VectorEnv) such that the original space's seed was ignored @pseudo-rnd-thoughts
- Added
AutoResetWrapper
that automatically callsEnv.reset
whenEnv.step
done is True @balisujohn
Minor changes
- BipedalWalker and LunarLander's observation spaces have non-infinite upper and lower bounds. @jjshoots
- Bumped the ALE-py version to
0.7.5
- Improved the performance of car racing through not rendering polygons off screen @andrewtanJS
- Fixed turn indicators that were black not red/white in Car racing @jjshoots
- Bug fixes for
VecEnvWrapper
to forward method calls to the environment @arjun-kg - Removed unnecessary try except on Box2d such that if
Box2d
is not installed correctly then a more helpful error is show @pseudo-rnd-thoughts - Simplified the
gym.registry
backend @RedTachyon - Re-added python 3.6 support through backports of python 3.7+ modules. This is not tested or compatible with the mujoco environments. @pseudo-rnd-thoughts
0.23.1#
Released on 2022-03-11 - GitHub - PyPI
This release contains a few small bug fixes and no breaking changes.
- Make
VideoRecorder
backward-compatible togym<0.23
by @vwxyzjn in #2678 - Fix issues with pygame event handling (which should fix support on windows and in jupyter notebooks) by @andrewtanJS in #2684
- Add py.typed to package_data by @micimize in https://github.com/openai/gym/p
- Fixes around 1500 warnings in CI @pseudo-rnd-thoughts
- Deprecation warnings correctly display now @vwxyzjn
- Fix removing striker and thrower @RushivArora
- Fix small dependency warning errorr @ZhiqingXiao
0.23.0#
Released on 2022-03-04 - GitHub - PyPI
This release contains many bug fixes and a few small changes.
Breaking changes:
- Standardized render metadata variables ahead of render breaking change @trigaten
- Removed deprecated monitor wrapper and associated dead code @gianlucadecola
- Unused striker and thrower MuJoCo envs moved to https://github.com/RushivArora/Gym-Mujoco-Archive @RushivArora
Many minor bug fixes (@vwxyzjn , @RedTachyon , @rusu24edward , @Markus28 , @dsctt , @andrewtanJS , @tristandeleu , @duburcqa)
0.22.0#
Released on 2022-02-17 - GitHub - PyPI
This release represents the largest set of changes ever to Gym, and represents a huge step towards the plans for 1.0 outlined here: #2524
Gym now has a new comprehensive documentation site: https://www.gymlibrary.ml/ !
API changes:
-env.reset
now accepts three new arguments:
options
- Usable for things like controlling curriculum learning without reinitializing the environment, which can be expensive (@RedTachyon)
seed
- Environment seeds can be passed to this reset argument in the future. The old .seed()
method is being deprecated in favor of this, though it will continue to function as before until the 1.0 release for backwards compatibility purposes (@RedTachyon)
infos
- when set to True
, reset will return obs, info. This currently defaults to False
, but will become the default behavior in Gym 1.0 (@RedTachyon)
-Environment names no longer require a version during registration and will suggest intelligent similar names (@kir0ul, @JesseFarebro)
-Vector environments now support terminal_observation in info
and support batch action spaces (@vwxyzjn, @tristandeleu)
Environment changes:
-The blackjack and frozen lake toy_text environments now have nice graphical rendering using PyGame (@1b15)
-Moved robotics environments to gym-robotics package (@seungjaeryanlee, @Rohan138, @vwxyzjn) (per discussion in #2456 (comment))
-The bipedal walker and lunar lander environments were consolidated into one class (@andrewtanJS)
-Atari environments now use standard seeding API (@JesseFarebro)
-Fixed large bug fixes in car_racing box2d environment, bumped version (@carlosluis, @araffin)
-Refactored all box2d and classic_control environments to use PyGame instead of Pyglet as issues with pyglet has been one of the most frequent sources of GitHub issues over the life of the gym project (@andrewtanJS)
Other changes:
-Removed DiscreteEnv class, built in environments no longer use it (@carlosluis)
-Large numbers of type hints added (@ikamensh, @RedTachyon)
-Python 3.10 support
-Tons of additional code refactoring, cleanup, error message improvements and small bug fixes (@vwxyzjn, @Markus28, @RushivArora, @jjshoots, @XuehaiPan, @Rohan138, @JesseFarebro, @Ericonaldo, @AdilZouitine, @RedTachyon)
-All environment files now have dramatically improved readmes at the top (that the documentation website automatically pulls from)
-As part of the seeding changes, Gym's RNG has been modified to use the np.random.Generator as the RandomState API has been deprecated. The methods randint, rand, randn are replaced by integers, random and standard_normal respectively. As a consequence, the random number generator has changed from MT19937 to PCG64.
v0.21.0: 0.21.0#
Released on 2021-10-02 - GitHub - PyPI
-The old Atari entry point that was broken with the last release and the upgrade to ALE-Py is fixed (@JesseFarebro)
-Atari environments now give much clearer error messages and warnings (@JesseFarebro)
-A new plugin system to enable an easier inclusion of third party environments has been added (@JesseFarebro)
-Atari environments now use the new plugin system to prevent clobbered names and other issues (@JesseFarebro)
-pip install gym[atari]
no longer distributes Atari ROMs that the ALE (the Atari emulator used) needs to run the various games. The easiest way to install ROMs into the ALE has been to use AutoROM. Gym now has a hook to AutoROM for easier CI automation so that using pip install gym[accept-rom-license]
calls AutoROM to add ROMs to the ALE. You can install the entire suite with the shorthand gym[atari, accept-rom-license]
. Note that as described in the name name, by installing gym[accept-rom-license]
you are confirming that you have the relevant license to install the ROMs. (@JesseFarebro)
-An accidental breaking change when loading saved policies trained on old versions of Gym with environments using the box action space have been fixed. (@RedTachyon)
-Pendulum has had a minor fix to it's physics logic made and the version has been bumped to v1 (@RedTachyon)
-Tests have been refactored into an orderly manner (@RedTachyon)
-Dict spaces now have standard dict helper methods (@Rohan138)
-Environment properties are now forwarded to the wrapper (@tristandeleu)
-Gym now properly enforces calling reset before stepping for the first time (@ahmedo42)
-Proper piping of error messages to stderr (@XuehaiPan)
-Fix video saving issues (@zlig)
Also, Gym is compiling a list of third party environments to into the new documentation website we're working on. Please submit PRs for ones that are missing: https://github.com/openai/gym/blob/master/docs/third_party_environments.md
v0.20.0: 0.20.0#
Released on 2021-09-14 - GitHub - PyPI
Major Change:
- Replaced Atari-Py dependency with ALE-Py and bumped all versions. This is a massive upgrade with many changes, please see the full explainer (@JesseFarebro)
- Note that ALE-Py does not include ROMs. You can install ROMs in two lines of bash with AutoROM though (
pip3 install autorom
and thenautorom
), see https://github.com/PettingZoo-Team/AutoROM. This is the recommended approach for CI, etc.
Breaking changes and new features:
- Add
RecordVideo
wrapper, deprecate monitor wrapper in favor of it andRecordEpisodeStatistics
wrapper (@vwxyzjn) - Dependencies used outside of environments (e.g. for wrappers) are now in 'other' extra' (@jkterry1)
- Moved algorithmic and unused toytext envs (guessing game, hotter colder, nchain, roulette, kellycoinflip) to third party repos (@jkterry1, @Rohan138)
- Fixed flatten utility and flatdim in MultiDiscrete sapce (@tristandeleu)
- Add
__setitem__
to dict space (@jfpettit) - Large fixes to .contains method for box space (@FirefoxMetzger)
- Made blackjack environment properly comply with Barto and Sutton book standard, bumped to v1 (@RedTachyon)
- Added
NormalizeObservation
andNormalizeReward
wrappers (@vwxyzjn) - Add
__getitem__
and__len__
to MultiDiscrete space (@XuehaiPan) - Changed .shape to be a property of box space to prevent unexpected behaviors (@RedTachyon)
Bug fixes and upgrades:
- Video recorder gracefully handles closing (@XuehaiPan)
- Remaining unnecessary dependencies in setup.py are resolved (@jkterry1)
- Minor acrobot performance improvements (@TuckerBMorgan)
- Pendulum properly renders when 0 force is sent (@Olimoyo)
- Make observations dtypes be consistent with observation space dtypes for all classic control envs and bipedalwalker (@RedTachyon)
- Removed unused and long depricated features in registration (@Rohan138)
- Framestack wrapper now inherits from obswrapper (@jfpettit)
- Seed method for
spaces.Tuple
andspaces.Dict
now properly function, are fully stochastic, are fully featured and behave in the expected manner (@XuehaiPan, @RaghuSpaceRajan) - Replace
time()
withperf_counter()
for better measurements of short duration (@zuoxingdong)
0.19.0#
Released on 2021-08-13 - GitHub - PyPI
Gym 0.19.0 is a large maintenance release, and the first since @jkterry1 became the maintainer. There should be no breaking changes in this release.
New features:
- Added custom datatype argument to multidiscrete space (@m-orsini)
- API compliance test added based on SB3 and PettingZoo tests (@amtamasi)
- RecordEpisodeStatics works with VectorEnv (@vwxyzjn)
Bug fixes:
- Removed unused dependencies, removed unnescesary dependency version requirements that caused installation issues on newer machines, added full requirements.txt and moved general dependencies to extras. Notably, "toy_text" is not a used extra. atari-py is now pegged to a precise working version pending the switch to ale-py (@jkterry1)
- Bug fixes to rewards in FrozenLake and FrozenLake8x8; versions bumped to v1 (@ZhiqingXiao)
-Removed remaining numpy depreciation warnings (@super-pirata) - Fixes to video recording (@mahiuchun, @zlig)
- EZ pickle argument fixes (@zzyunzhi, @Indoril007)
- Other very minor (nonbreaking) fixes
Other:
0.12.5: Fixed fetch/slide#
v0.9.6: Cleanup + Remove Unmaintained Code#
Released on 2018-02-01 - GitHub - PyPI
- Now your
Env
andWrapper
subclasses should definestep
,reset
,render
,close
,seed
rather than underscored method names. - Removed the
board_game
,debugging
,safety
,parameter_tuning
environments since they're not being maintained by us at OpenAI. We encourage authors and users to create new repositories for these environments. - Changed
MultiDiscrete
action space to range from[0, ..., n-1]
rather than[a, ..., b-1]
. - No more
render(close=True)
, use env-specific methods to close the rendering. - Removed
scoreboard
directory, since site doesn't exist anymore. - Moved
gym/monitoring
togym/wrappers/monitoring
- Add
dtype
toSpace
. - Not using python's built-in module anymore, using
gym.logger