tensor-optix 1.2.2__tar.gz → 1.2.3__tar.gz

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tensor-optix
-Version: 1.2.2
+Version: 1.2.3
 Summary: Autonomous training loop for any sequential learning model — built-in PPO, DQN, and SAC for TensorFlow and PyTorch
 Author: sup3rus3r
 License-Expression: MIT

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tensor-optix"
-version = "1.2.2"
+version = "1.2.3"
 description = "Autonomous training loop for any sequential learning model — built-in PPO, DQN, and SAC for TensorFlow and PyTorch"
 readme = "README.md"
 license = "MIT"

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/tensor_optix/algorithms/tf_ppo.py

@@ -291,6 +291,16 @@ class TFPPOAgent(BaseAgent):
     # Internal helpers
     # ------------------------------------------------------------------
 
+    def reset_cache(self) -> None:
+        """
+        Discard all entries in the rollout cache without learning from them.
+        Called by LoopController after a val-pipeline window is collected, so
+        that val-rollout entries never bleed into the next training learn() call.
+        """
+        self._cache_obs.clear()
+        self._cache_log_probs.clear()
+        self._cache_values.clear()
+
     def _clear_cache(self, T: int) -> None:
         del self._cache_obs[:T]
         del self._cache_log_probs[:T]

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/tensor_optix/algorithms/tf_ppo_continuous.py

@@ -319,6 +319,12 @@ class TFGaussianPPOAgent(BaseAgent):
             for v in module.trainable_variables:
                 v.assign(v * (1.0 + noise_scale * tf.random.normal(v.shape)))
 
+    def reset_cache(self) -> None:
+        """Discard all rollout cache entries without learning from them."""
+        self._cache_obs.clear()
+        self._cache_log_probs.clear()
+        self._cache_values.clear()
+
     @staticmethod
     def _explained_variance(values: np.ndarray, returns: np.ndarray) -> float:
         var_returns = float(np.var(returns))

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/tensor_optix/algorithms/torch_ppo.py

@@ -275,6 +275,12 @@ class TorchPPOAgent(BaseAgent):
                 for param in module.parameters():
                     param.mul_(1.0 + noise_scale * torch.randn_like(param))
 
+    def reset_cache(self) -> None:
+        """Discard all rollout cache entries without learning from them."""
+        self._cache_obs.clear()
+        self._cache_log_probs.clear()
+        self._cache_values.clear()
+
     @staticmethod
     def _explained_variance(values: np.ndarray, returns: np.ndarray) -> float:
         var_returns = float(np.var(returns))

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/tensor_optix/algorithms/torch_ppo_continuous.py

@@ -343,6 +343,12 @@ class TorchGaussianPPOAgent(BaseAgent):
                 for param in module.parameters():
                     param.mul_(1.0 + noise_scale * torch.randn_like(param))
 
+    def reset_cache(self) -> None:
+        """Discard all rollout cache entries without learning from them."""
+        self._cache_obs.clear()
+        self._cache_log_probs.clear()
+        self._cache_values.clear()
+
     @staticmethod
     def _explained_variance(values: np.ndarray, returns: np.ndarray) -> float:
         var_returns = float(np.var(returns))

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/tensor_optix/core/loop_controller.py

@@ -227,6 +227,11 @@ class LoopController:
                     val_episode = next(self._val_gen)
                     val_episode.episode_id = episode_id
                     val_metrics = self._evaluator.score_validation(val_episode)
+                    # Val pipeline calls agent.act() to collect rollouts, which
+                    # populates the on-policy rollout cache. That data must never
+                    # be consumed by the next training learn() call. Clear it now.
+                    if hasattr(self._agent, "reset_cache"):
+                        self._agent.reset_cache()
                     eval_metrics = self._evaluator.combine(train_metrics, val_metrics)
                     eval_metrics.episode_id = episode_id
                     logger.debug(

{tensor_optix-1.2.2 → tensor_optix-1.2.3}/tensor_optix.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tensor-optix
-Version: 1.2.2
+Version: 1.2.3
 Summary: Autonomous training loop for any sequential learning model — built-in PPO, DQN, and SAC for TensorFlow and PyTorch
 Author: sup3rus3r
 License-Expression: MIT