Merge branch 'master' into feat/mps-support

docs/misc/changelog.rst

@@ -21,12 +21,14 @@ Bug Fixes:
 - Fixed the issue that ``predict`` does not always return action as ``np.ndarray`` (@qgallouedec)
 - Fixed division by zero error when computing FPS when a small number of time has elapsed in operating systems with low-precision timers.
 - Added multidimensional action space support (@qgallouedec)
+- Fixed missing verbose parameter passing in the ``EvalCallback`` constructor (@burakdmb)
 
 Deprecations:
 ^^^^^^^^^^^^^
 
 Others:
 ^^^^^^^
+- Fixed ``DictReplayBuffer.next_observations`` typing (@qgallouedec)
 
 Documentation:
 ^^^^^^^^^^^^^^
@@ -1019,4 +1021,4 @@ And all the contributors:
 @eleurent @ac-93 @cove9988 @theDebugger811 @hsuehch @Demetrio92 @thomasgubler @IperGiove @ScheiklP
 @simoninithomas @armandpl @manuel-delverme @Gautam-J @gianlucadecola @buoyancy99 @caburu @xy9485
 @Gregwar @ycheng517 @quantitative-technologies @bcollazo @git-thor @TibiGG @cool-RR @MWeltevrede
-@Melanol @qgallouedec @francescoluciano @jlp-ue
+@Melanol @qgallouedec @francescoluciano @jlp-ue @burakdmb

stable_baselines3/common/base_class.py

@@ -392,6 +392,7 @@ class BaseAlgorithm(ABC):
                 log_path=log_path,
                 eval_freq=eval_freq,
                 n_eval_episodes=n_eval_episodes,
+                verbose=self.verbose,
             )
             callback = CallbackList([callback, eval_callback])
 

stable_baselines3/common/type_aliases.py

@@ -50,7 +50,7 @@ class ReplayBufferSamples(NamedTuple):
 class DictReplayBufferSamples(ReplayBufferSamples):
     observations: TensorDict
     actions: th.Tensor
-    next_observations: th.Tensor
+    next_observations: TensorDict
     dones: th.Tensor
     rewards: th.Tensor