* Implement PixelObservationWrapper
* Change MujocoEnv.render to support custom camera_{name,id}
* Implement tests for PixelObservationWrapper
* Use env.get_pixels instead of direct env.render
* Fix camera_{id,name} check in pixel observation wrapper
* Fix rendering with explicit camera_id
* Add Wrapperget_pixels to allow call to be propagated to wrapped env
* Remove use of unnecessary `get_pixels` method
* Update PixelObservationWrapper to support multiple pixel keys
* Remove unnecessary `rgb_rendering_tracking` argument
* Remove rgb_rendering_tracking logic
* switch rgb_array camera to 0
* merge latest master
* add tracking camera for swimmer
* test track camera name to be in valid names
* add rgb_rendering_tracking kwarg to locomotion mujoco envs; fixes 1135
* fix track camera logic in mujoco_env.py
* remove vertical camera motion on env.reset()
* In MuJoCo envs, don't reset viewers on environment reset. If the user moves around the camera in the viewer, allow them to keep the camera wherever they put it.
* Docstring update.
* pass device_id=-1 when rendering mujoco in rgb_array mode
* trying ubuntu18.04 build
* use travis build matrix
* use travis build matrix
* use travis build matrix
* use fix 18.04 installation steps
* use fix 18.04 installation steps
* try py3 instead of py35
* trying the 14.04 build; cleaning up the 16.04 package list
* fixes to dockerfile.14.04
* fixes to dockerfile.14.04
* fixes to dockerfile.14.04
* fixes to dockerfile.14.04
* fixes to dockerfile.14.04
* fixing system package list for 14.04
* 16.04 build working
* clean up test.dockerfile.16.04
* adding python-numpy system package
* add patchelf
* remove python-numpy from 16.04 dockerfile
* 14.04 does not use mujoco (patchelf problem)
* cleaning up 18.04 dockerfile
* added comment to 14.04 dockerfile
* fix syntax in 14.04 dockerfile
* being fancy and switching from apt-get to apt command in 18.04 dockerfile
* update README.rst to use apt (instead of apt-get) on ubuntu 18.04
* Add depth rendering from camera
Allow the mujoco renderer to return the depth image using the `depth_array` mode.
It follows the `rgb_array` extraction method.
* Depth data is a 2d array.
* Add depth_array to render modes.
* build test image from scratch from ubuntu:16.04
* removed pulling old image from .travis.yml
* try installing keyboard-configuration on docker on travis
* trying install keyboard-configuration before rest of the packages
* upgrading dockerfile and entrypoint to work with ubuntu16.04
* fixing dummy display config wip
* install keyboard-properties first in dockerfile
* pass mujoco_key in .travis.yml
* skipsdist in tox.ini
* removed unpacking of the mujoco bundle in entrypoint
* using xvfb for fake display
* comment out self.viewer.close
* install ffmpeg
* squash run commands in dockerfile
* fixed typo in dockerfile
* fixed typo in dockerfile
* fixed typo in dockerfile
* use self.np_random in robotics/hand/manipulate
* some cleanups in .travis.yml
* cleaning up accidental changes
* cleaning up accidental changes
* inject mujoco key on runtime (instead of container buildtime)
* remove webhooks section from .travis.yml
* add dtype to Box
* remove board_game, debugging, safety, parameter_tuning environments
* massive set of breaking changes
- remove python logging module
- _step, _reset, _seed, _close => non underscored method
- remove benchmark and scoring folder
* Improve render("human"), now resizable, closable window.
* get rid of default step and reset in wrappers, so it doesn’t silently fail for people with underscore methods
* CubeCrash unit test environment
* followup fixes
* MemorizeDigits unit test envrionment
* refactored spaces a bit
fixed indentation
disabled test_env_semantics
* fix unit tests
* fixes
* CubeCrash, MemorizeDigits tested
* gym backwards compatibility patch
* gym backwards compatibility, followup fixes
* changelist, add spaces to main namespaces
* undo_logger_setup for backwards compat
* remove configuration.py
* all envs run offscreen
* render works
* changed mujoco-py version
* Bump versions
* Update version and README
* Same versioning for all mujoco envs
* Fix typo
* Fix version
* Bump version again
* Revert "Fix version"
This reverts commit decc5779811801deb6ae9fad697dfe247d2bdd94.
* Make environments seedable
* Fix monitor bugs
- Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors.
- Remove extra pid from stats recorder filename. This should be purely cosmetic.
* Start uploading seeds in episode_batch
* Fix _bigint_from_bytes for python3
* Set seed explicitly in random_agent
* Pass through seed argument
* Also pass through random state to spaces
* Pass random state into the observation/action spaces
* Make all _seed methods return the list of used seeds
* Switch over to np.random where possible
* Start hashing seeds, and also seed doom engine
* Fixup seeding determinism in many cases
* Seed before loading the ROM
* Make seeding more Python3 friendly
* Make the MuJoCo skipping a bit more forgiving
* Remove debugging PDB calls
* Make setInt argument into raw bytes
* Validate and upload seeds
* Skip box2d
* Make seeds smaller, and change representation of seeds in upload
* Handle long seeds
* Fix RandomAgent example to be deterministic
* Handle integer types correctly in Python2 and Python3
* Try caching pip
* Try adding swap
* Add df and free calls
* Bump swap
* Bump swap size
* Try setting overcommit
* Try other sysctls
* Try fixing overcommit
* Try just setting overcommit_memory=1
* Add explanatory comment
* Add what's new section to readme
* BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now
* Document seed
* Move nondetermistic check into spec
