Jiminy-py

<p align="center"> <img src="https://user-images.githubusercontent.com/17752950/136691724-722d1522-8e24-44fc-85a1-c72e25a49f6b.gif" height="180"> <img src="https://user-images.githubusercontent.com/17752950/136691341-19d558a4-4b52-4abe-b0da-6e841495c4c0.png" height="180"> <img src="https://user-images.githubusercontent.com/17752950/136691348-1c449fed-6fc6-4126-b9ce-303143e4d922.png" height="180"></p>

Up to now, several key features were missing for the impulse-based LCP contact model to support most cases, and LCP solver was not mature enough to ensure smooth continuous dynamics. The impulse contact model now can handle any contact normal, which makes it suitable for uneven grounds. Moreover, a fast random tile ground generator has been added to easily create parametric challenging environments suitable for curriculum learning. Ultimately, the rendering of engine ground profile is now fully integrated in the viewer for panda3d backend. It will automatically renders the actual ground profile during replay of simulations. The minor release tag has been updated to highlight that impulse contact model is no longer experimental.

New features

* [core] Add support of torsional friction and contact normal to impulse contact model.
* [python/generator] Add random tile ground profile generator.
* [python/viewer] Add support of contact frames display.
* [python/viewer] Add method to render floor based on 'HeatMapFunctor'.
* [python/simulator] 'replay' now display the ground profile used by the engine.
* [gym/rllib] Add temporal barrier regularizer to PPO.

Improvements

* [core] Move init of contact solver in reset instead of setOptions.
* [core] Proper default 'stabilizationFreq' for impulse contact model.
* [core] 'engine_options.contacts.stabilizationFreq' only applies to contact constraints.
* [python/viewer] 'update_floor' method in panda3d now expects numpy array instead of callable to fix serialization issues.
* [python/viewer] Speedup rendering of ground profile and improve visual by providing normal to panda3d.
* [python/viewer] Add option to enable/disable display of ground profile meshes.
* [python/simulator] Do not reset camera pose if gui already available.

Patches and bug fixes

* [python/robot] Fix support of URDF model with a single link for automatic hardware config generation.
* [python/viewer] Add support of ipykernel 6 for meshcat backend interactive display.
* [python/dynamics] Mitigate a weird segfault in pinocchio bindings of 'centerOfMass' method.
* [gym/common] Fix automatic telemetry registration of the action.

Miscellaneous

* [gym/envs] Set baumgarte frequency for cassie internal constraints.
* [misc] Enforce scipy>=1.2.0 to fix buggy optimizer.
* [misc] Update 'typing_extensions' required version to fix pylint support for Python 3.6.

Meshcat viewer backend was mostly unmaintained since a year and was partially broken. This should now be fixed, with the addition of 3D rendering directly inside local VSCode notebooks and local Jupyterlab !

New features

* [python/viewer] Add height map rendering capability to Panda3d backend.
* [python/viewer] Add support of jupyterlab and vscode notebooks locally using Meshcat backend.
* [gym/common] Add flag to 'play_interactive' to ignore 'is_done' state.
* [gym/rllib] Support obs normalization for PPO spatial regularization.
* [gym/rllib] Scale spatial loss by observation distance.

Improvements

* [core] Shuffle constraint solver iterations iif necessary, no matter if constraint set changes.
* [core] Move contact point at the interface with the ground for impulse model. (404)
* [python/viewer] Properly close opening viewer if raises exception at init.
* [gym/common] Check that simulation data is available before plotting.
* [gym/rllib] Raise clear exception if observation space is not dict in PPO.
* [gym/rllib] Replace L2-norm temporal smoothness regularization by L1-norm.

Patches and bug fixes

* [core/python] Fix bindings signature of some controller's method.
* [python/plot] Fix missing grid for single plot tabs.
* [python/viewer] Fix viewer compatibility with meshcat>=0.3.1.
* [python/viewer] Fix meshcat viewer 'has_gui' method.
* [python/viewer] Fix meshcat notebook viewer.
* [gym/common] Fix 'play_interactive' not disabling 'is_training' flag.
* [gym/rllib] Fix L2 reg not backpropagating gradient.

Miscellaneous

* [python/viewer] Increase meshcat recorder timeout.
* [misc] Fix CI dependency install.
* [misc] Relax ray version requirement.

Small release fixing reproducibility issues, and updating RLlib tools to make it easier to assess and compare performance between policies.

New features

* [gym/common] Add train and eval modes to allow specific evaluation behaviors.
* [gym/rllib] Add l2 regulization loss to PPO.
* [gym/rllib] Enable to evaluate policy on multiple trials and report statistics.

Improvements

* [gym/common] 'seed' method now return the actual sequence of seeds instead of only the first one.
* [gym/common] Do not cast automatically the action space to float32. (400)
* [gym/toolbox] Add 'quat_to_yaw_cos_sin' math helper.
* [gym/rllib] Use noisy samples instead of the true ones to compute global smoothness.
* [gym/rllib] Make sure the validation is always the same to make it easier to benchmark performance.

Patches and bug fixes

* [core] Fix log buffer not refreshed after calling 'stop', making last datapoint not accessible. (396)
* [python/robot] Fix non-reproducible simulation results.
* [python/simulator] Fix running simulation not stopped before updating seed.
* [python/simulator] Fix unexpected error if 'replay' is called without data.
* [gym/common] Ensure internal '_action' buffer dtype float64. (400)

Miscellaneous

* [gym/common] Do not set the seed by default in '_setup' method.
* [gym/common] Rename '_is_training' in 'is_training'. Fix 'is_training' False by default. (397)
* [gym/common] Remove useless conversion of iterator to list.
* [gym/rllib] Relax ray dependency version requirement.

This release fixes a new non-critical bugs and contains some minor improvements for gym tools suite.

Improvements

* [gym/common] More efficient random number generator.
* [gym/common] Reset internal '_info' buffer before calling 'is_done' to enable storing extra info. (386)
* [gym/common] Faster space 'clip' utility.
* [gym/common] Do not automatically disable telemetry anymore.
* [gym/common] Enable 'refresh_observation' to access up-to-date shared internal data. (384)
* [gym/common] '_setup' updates frame kinematics for neutral configuration by default.
* [gym/toolbox] Add more convex hull utilities.
* [gym/toolbox] Add math utilities to extract yaw only from transform.

Patches and bug fixes

* [core] Fix model parameters random sampling.
* [core] Make sure random physics parameters are valid.
* [python/simulator] Fix default external force display during replay.
* [python/viewer] Fix support of robot without sensors nor freeflyer.
* [python/viewer] Check that 'time_interval' is valid. Fix out-of-range edge case.
* [gym/common] Various minor bug fixes.
* [gym/toolbox] Fix computation of distance from convex hull.
* [gym/rllib] Fix connection of existing ray cluster head.
* [gym/rllib] Clip random obs to space bounds in PPO regularization.
* [gym/rllib] Fix support of non-dict obs space for 'build_policy_wrapper'.

Miscellaneous

* [misc] Add mass fixed frame with visual to cartpole.
* [misc] Disable warnings when building SOUP. (378)
* [misc] Fix push gym_jiminy wheels on pypi. (379)
* [misc] Fix support of python virtual env for easy-install script. (383)

All unnecessary copies and function calls in learning pipelines are now avoided. In additional, Python architecture has been refactored to reduce dependencies of main packages `jiminy_py`, `gym_jiminy_common`, and `gym_jiminy_toolbox`.

New features

* [gym/common] Allow to specify custom observer update period for base env to avoid refresh observation during internal steps.
* [gym/common] Add optional '_refresh_internal' method to share computation between 'is_done' and 'compute_reward'.

Improvements

* [gym/common] Improve performance by avoiding deepcopy of action in 'compute_command' methods.
* [gym/toolbox] More versatile compute action helper for rllib. (373)

Patches and bug fixes

Miscellaenous

* [python] Remove unused/unmaintained 'smoothing_filter' processing helper.
* [misc] More generic github action wheel generation script. (375)
* [misc] Move 'processing' module from 'jiminy_py' to 'gym_jiminy.toolbox' to remove numba deps.
* [misc] Move 'rllib' module from 'gym_jiminy.toolbox' to a dedicated 'gym_jiminy.rllib' package to remove rllib deps.

Small release fixing a few minor bugs.

Improvements

* [python/dynamics] Remove useless joint jacobians computation.

Patches and bug fixes

* [core/python] Fix bindings of pinocchio overloads.
* [python/viewer] Fix calls to super in Panda3dQWidget (370)
* [misc] Do not try pushing legacy wheels on pypi. (368)