Merge branch 'master' into patch-1

DLR-RM · May 3, 2024 · 126c3d2 · 126c3d2
2 parents 4fc16bd + 285e01f
commit 126c3d2
Show file tree

Hide file tree

Showing 4 changed files with 28 additions and 7 deletions.
diff --git a/docs/guide/tensorboard.rst b/docs/guide/tensorboard.rst
@@ -192,6 +192,7 @@ Here is an example of how to render an episode and log the resulting video to Te
 
     import gymnasium as gym
     import torch as th
+    import numpy as np
 
     from stable_baselines3 import A2C
     from stable_baselines3.common.callbacks import BaseCallback
@@ -226,6 +227,9 @@ Here is an example of how to render an episode and log the resulting video to Te
                     :param _locals: A dictionary containing all local variables of the callback's scope
                     :param _globals: A dictionary containing all global variables of the callback's scope
                     """
+                    # We expect `render()` to return a uint8 array with values in [0, 255] or a float array
+                    # with values in [0, 1], as described in
+                    # https://pytorch.org/docs/stable/tensorboard.html#torch.utils.tensorboard.writer.SummaryWriter.add_video
                     screen = self._eval_env.render(mode="rgb_array")
                     # PyTorch uses CxHxW vs HxWxC gym (and tensorflow) image convention
                     screens.append(screen.transpose(2, 0, 1))
@@ -239,7 +243,7 @@ Here is an example of how to render an episode and log the resulting video to Te
                 )
                 self.logger.record(
                     "trajectory/video",
-                    Video(th.ByteTensor([screens]), fps=40),
+                    Video(th.from_numpy(np.asarray([screens])), fps=40),
                     exclude=("stdout", "log", "json", "csv"),
                 )
             return True

diff --git a/docs/misc/changelog.rst b/docs/misc/changelog.rst
@@ -14,6 +14,7 @@ New Features:
 
 Bug Fixes:
 ^^^^^^^^^^
+- Fix memory leak when loading learner from storage (@peteole)
 
 `SB3-Contrib`_
 ^^^^^^^^^^^^^^
@@ -35,28 +36,43 @@ Bug Fixes:
 
 Documentation:
 ^^^^^^^^^^^^^^
-- Added ER-MRL to the project page
+
+Release 2.3.2 (2024-04-27)
+--------------------------
+
+Bug Fixes:
+^^^^^^^^^^
+- Reverted ``torch.load()`` to be called ``weights_only=False`` as it caused loading issue with old version of PyTorch.
+
+
+Documentation:
+^^^^^^^^^^^^^^
+- Added ER-MRL to the project page (@corentinlger)
+- Updated Tensorboard Logging Videos documentation (@NickLucche)
 
 
 Release 2.3.1 (2024-04-22)
 --------------------------
 
 Bug Fixes:
 ^^^^^^^^^^
-- Fix memory leak when loading learner from storage (@peteole)
 - Cast return value of learning rate schedule to float, to avoid issue when loading model because of ``weights_only=True`` (@markscsmith)
 
 Documentation:
 ^^^^^^^^^^^^^^
 - Updated SBX documentation (CrossQ and deprecated DroQ)
 - Updated RL Tips and Tricks section
 
-
 Release 2.3.0 (2024-03-31)
 --------------------------
 
 **New defaults hyperparameters for DDPG, TD3 and DQN**
 
+.. warning::
+
+  Because of ``weights_only=True``, this release breaks loading of policies when using PyTorch 1.13.
+  Please upgrade to PyTorch >= 2.0 or upgrade SB3 version (we reverted the change in SB3 2.3.2)
+
 
 Breaking Changes:
 ^^^^^^^^^^^^^^^^^
@@ -1642,4 +1658,4 @@ And all the contributors:
 @anand-bala @hughperkins @sidney-tio @AlexPasqua @dominicgkerr @Akhilez @Rocamonde @tobirohrer @ZikangXiong @ReHoss
 @DavyMorgan @luizapozzobon @Bonifatius94 @theSquaredError @harveybellini @DavyMorgan @FieteO @jonasreiher @npit @WeberSamuel @troiganto
 @lutogniew @lbergmann1 @lukashass @BertrandDecoster @pseudo-rnd-thoughts @stefanbschneider @kyle-he @PatrickHelm @corentinlger
-@marekm4 @stagoverflow @rushitnshah @markscsmith @peteole
+@marekm4 @stagoverflow @rushitnshah @markscsmith @NickLucche @peteole
diff --git a/stable_baselines3/common/save_util.py b/stable_baselines3/common/save_util.py
@@ -447,7 +447,8 @@ def load_from_zip_file(
                     file_content.seek(0)
                     # Load the parameters with the right ``map_location``.
                     # Remove ".pth" ending with splitext
-                    th_object = th.load(file_content, map_location=device, weights_only=True)
+                    # Note(antonin): we cannot use weights_only=True, as it breaks with PyTorch 1.13, see GH#1911
+                    th_object = th.load(file_content, map_location=device, weights_only=False)
                     # "tensors.pth" was renamed "pytorch_variables.pth" in v0.9.0, see PR #138
                     if file_path == "pytorch_variables.pth" or file_path == "tensors.pth":
                         # PyTorch variables (not state_dicts)

diff --git a/stable_baselines3/version.txt b/stable_baselines3/version.txt
@@ -1 +1 @@
-2.4.0a0
+2.3.2