David Blom 3efab0d267 Training and evaluation: call model.train() and model.eval() (#537) ... * 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>		2021-08-14 14:08:27 +02:00
..
a2c	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00
common	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00
ddpg	Fix type annotations (#522)	2021-07-29 13:02:09 +02:00
dqn	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00
her	Dictionary Observations (#243)	2021-05-11 12:29:30 +02:00
ppo	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00
sac	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00
td3	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00
__init__.py	Dictionary Observations (#243)	2021-05-11 12:29:30 +02:00
py.typed	Rename to stable-baselines3	2020-05-05 15:02:35 +02:00
version.txt	Training and evaluation: call model.train() and model.eval() (#537)	2021-08-14 14:08:27 +02:00