* more verbose documentation regarding `.load` vs `.set_parameters` (#683, #614)
* add a note to explain the difference between `.load` and `.set_parameters` to the examples
* fix typos
Co-authored-by: Anssi <kaneran21@hotmail.com>
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Added ``newline="\n"`` when opening CSV monitor files so that each line ends with ``\r\n`` instead of ``\r\r\n`` on Windows while Linux environments are not affected
* Add multi-env training support for SAC
* Fix for dict obs
* Pytype fixes
* Fix assert on number of envs
* Remove for loop
* Add support for Dict obs
* Start cleanup
* Update doc and bug fix
* Add support for vectorized action noise
and add multi env example for off-policy
* Update version
* Bug fix with VecNormalize
* Update README table
* Update variable names
* Update changelog and version
* Update doc and fix for `gradient_steps=-1`
* Add test for `gradient_steps=-1`
* Disable pytype pyi errors
* Fix for DQN
* Update comment on deepcopy
* Remove episode_reward field
* Fix RolloutReturn
* Avoid modification by reference
* Fix error message
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Fix evaluation script for RNN
* Add error message
* Revert "Add error message"
This reverts commit 8d69b6cf4de2cd13aecfb425bd3145fad6a6c49a.
* Fix for pytype
* Rename mask to `episode_start`
* Fix type hint
* Fix type hints
* Remove confusing part of sentence
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Add a section on exporting to TFLite/Coral with demonstration
* Changelog to reflect new export documentation
* Update docs/guide/export.rst
Fingers on autopilot make word wrong
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Update docs/guide/export.rst
Better wording clarity
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Update docs/guide/export.rst
Better wording clarity
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Clarify motivations and hardware
* Update docs/misc/changelog.rst
Make consistent with other changelog entries
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Sphinx wants the section underline to be at least this long
* Remove first-person voice
* Typos
Co-authored-by: Anssi <kaneran21@hotmail.com>
* Update rl_tips.rst
indent fix to make if done and its following statement work
* Fix indentation and update changelog
* Skip type check for python 3.9
Co-authored-by: paulg <cove9988@gmail.com>
* Store number of timesteps at the beginning of each learn cycle
* Update changelog
* Set default _num_timesteps_at_start in the contructor
* Test case for FPS logger
* Adjust test to cover both on-policy and off-policy algorithms
* Fix formatting
* Update test and add comment
* Fix test
Co-authored-by: Oleksii Kachaiev <okachaiev@riotgames.com>
Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
* Add highway-env to the list of projects using SB3
Many thanks for this fantastic library, keep up the good work!
* Update changelog with added documentation
* Add `system_env_info`
* Add `print_system_info` to load
and store system info at save time
* Remove TODO
* Rename to `get_system_info`
* Import as sb3 for consistency
* Update changelog
* Add warning for old SB3 versions
* Use underscore litteral for more clarity
* Use a consistent key to log the total timesteps
This changes the timestep logging key of on-policy algorithms from
`time/total_timesteps` to `time/total timesteps` (note the
underscore/space). The off-policy algorithms and the eval callback
already use the latter, so this behavior is more consistent.
* Use underscores instead of spaces in logging keys
Most keys already followed this policy and consistent behavior is
friendlier to new users.
* Minor edit and bump version
Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
* Updated ONNX documentation
First draft on the documentation explaining how to export SB3 models in the ONNX format
* Updated changelog with ONNX documentation fix
* Address comments
* Update changelog.rst
* Update rtd env
* Fixes + add test example
Co-authored-by: Antonin RAFFIN <antonin.raffin@ensta.org>
Co-authored-by: Anssi Kanervisto <anssk@Anssis-MacBook-Air.local>
Co-authored-by: Anssi Kanervisto <kaneran21@hotmail.com>
* VecNormalize: allow non-continuous observations when norm_obs is False
* Update changelog, fix lint
* Switch to environment present in new and old versions of Gym
* Fix name
Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
* feat: add method predict_values for ActorCriticPolicy
* Fixes for new gym version
* Reformat
Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
* feat: get_distribution method for ActorCriticPolicy
New method get_distribution for class ActorCriticPolicy returning current action distribution given observations
* doc: updating changelog.rst
- adding block for Release 1.2.1a0
- adding cyprienc to contributors
* style: make format
* fix: updating version.txt
Changing version from 1.2.0 to 1.2.1a0
* Update changelog
* Add test for get distribution
Co-authored-by: Cyprien <courtot.c@gmail.com>
* make sure DQN policy is always in correct mode - train or eval
* make set_training_mode an abstract method of the base policy - safer
* update docstring of _build method to note that the target network is put into eval mode
* use set_training_mode to put the dqn target network into eval mode
* use set_training_mode to set the training model of the q-network
* move set_training_mode abstract method from BasePolicy to BaseModel
* set train and eval mode for TD3
* make sure critic is always in correct mode during train
* set train and eval mode for SAC
* add comment re batch norm and dropout
* set train and eval mode for A2C and PPO
* add tests for collect rollouts with batch norm
* fix formatting
* update change log
* update version
* remove Optional typing for batch size - causing type check to fail
* Fix scipy dependency for toy text envs
* implement set_training_mode method in BaseModel
* move all tests of train/eval mode to test_train_eval_mode
* call learn with learning_starts = total_timesteps to test that collect_rollouts does not update batch norm
* remove extra calls to set_training_mode in train method of TD3 and SAC
* Allow gradient_steps=0
* Refactor tests
* Add comment + use aliases
* Typos
Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
* training and evaluation: call model.train() and model.eval() to enable and disable dropout and batchnorm
* Add comment documentation
* Fix train and eval for the Actor class
* Run black
* Add github handle to changelog
* Add unit tests for PPO and DQN
* Refactor unit test
* Run black
* unit test: add a dropout layer and check that calling predict with deterministic=True is deterministic
* documentation: add bugfix description to changelog
* unit test: use learning_starts=0, decrease the size of the network and use more training steps
* on policy algorithms: call policy.train() and policy.eval() instead of disable_training and enable_training as it is a th.nn.module
* Rename unit test
* unit test: use drop out probability of 0.5
* Call policy.train and policy.eval
* Fixes + update tests
* Remove unneeded eval
Co-authored-by: David Blom <davidsblom@gmail.com>
Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>
