From a10e3ae5870836ed38e0b65c4176bbec3f22a1cb Mon Sep 17 00:00:00 2001 From: Antonin RAFFIN Date: Sun, 4 Oct 2020 17:12:35 +0200 Subject: [PATCH] Release v0.9.0 (#174) --- docs/misc/changelog.rst | 5 ++++- stable_baselines3/dqn/dqn.py | 3 +++ stable_baselines3/version.txt | 2 +- 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst index d74b402..3ee445b 100644 --- a/docs/misc/changelog.rst +++ b/docs/misc/changelog.rst @@ -3,9 +3,11 @@ Changelog ========== -Pre-Release 0.9.0a2 (WIP) +Pre-Release 0.9.0 (2020-10-03) ------------------------------ +**Bug fixes, get/set parameters and improved docs** + Breaking Changes: ^^^^^^^^^^^^^^^^^ - Removed ``device`` keyword argument of policies; use ``policy.to(device)`` instead. (@qxcv) @@ -50,6 +52,7 @@ Others: - Clarified docstrings on what is saved and loaded to/from files - Simplified ``save_to_zip_file`` function by removing duplicate code - Store library version along with the saved models +- DQN loss is now logged Documentation: ^^^^^^^^^^^^^^ diff --git a/stable_baselines3/dqn/dqn.py b/stable_baselines3/dqn/dqn.py index 29323c0..55fb835 100644 --- a/stable_baselines3/dqn/dqn.py +++ b/stable_baselines3/dqn/dqn.py @@ -147,6 +147,7 @@ class DQN(OffPolicyAlgorithm): # Update learning rate according to schedule self._update_learning_rate(self.policy.optimizer) + losses = [] for gradient_step in range(gradient_steps): # Sample replay buffer replay_data = self.replay_buffer.sample(batch_size, env=self._vec_normalize_env) @@ -169,6 +170,7 @@ class DQN(OffPolicyAlgorithm): # Compute Huber loss (less sensitive to outliers) loss = F.smooth_l1_loss(current_q, target_q) + losses.append(loss.item()) # Optimize the policy self.policy.optimizer.zero_grad() @@ -181,6 +183,7 @@ class DQN(OffPolicyAlgorithm): self._n_updates += gradient_steps logger.record("train/n_updates", self._n_updates, exclude="tensorboard") + logger.record("train/loss", np.mean(losses)) def predict( self, diff --git a/stable_baselines3/version.txt b/stable_baselines3/version.txt index 63aaf3d..ac39a10 100644 --- a/stable_baselines3/version.txt +++ b/stable_baselines3/version.txt @@ -1 +1 @@ -0.9.0a2 +0.9.0