diff --git a/docs/source/libero.mdx b/docs/source/libero.mdx
index 6dba5c62e..880a18d60 100644
--- a/docs/source/libero.mdx
+++ b/docs/source/libero.mdx
@@ -92,6 +92,20 @@ LIBERO supports two control modes — `relative` (default) and `absolute`. Diffe
 --env.control_mode=relative   # or "absolute"
 ```
 
+### Reset performance
+
+By default, LeRobot preserves LIBERO's hard-reset behavior. With fixed initial
+states enabled, you can opt into soft resets to skip rebuilding the simulator
+model and renderer on every episode:
+
+```bash
+--env.init_states=true --env.hard_reset=false
+```
+
+Soft resets are faster but are not bit-identical to hard resets after the
+environment's settling steps, so camera observations and policy results may
+differ slightly. Use hard resets when reproducing benchmark results.
+
 ### Policy inputs and outputs
 
 **Observations:**
diff --git a/docs/source/libero_plus.mdx b/docs/source/libero_plus.mdx
index b065649fa..173b81255 100644
--- a/docs/source/libero_plus.mdx
+++ b/docs/source/libero_plus.mdx
@@ -134,6 +134,20 @@ LIBERO-plus supports two control modes — `relative` (default) and `absolute`.
 --env.control_mode=relative   # or "absolute"
 ```
 
+### Reset performance
+
+By default, LeRobot preserves LIBERO's hard-reset behavior. With fixed initial
+states enabled, you can opt into soft resets to skip rebuilding the simulator
+model and renderer on every episode:
+
+```bash
+--env.init_states=true --env.hard_reset=false
+```
+
+Soft resets are faster but are not bit-identical to hard resets after the
+environment's settling steps, so camera observations and policy results may
+differ slightly. Use hard resets when reproducing benchmark results.
+
 ### Policy inputs and outputs
 
 **Observations:**
diff --git a/src/lerobot/envs/configs.py b/src/lerobot/envs/configs.py
index 3c210052f..312b02625 100644
--- a/src/lerobot/envs/configs.py
+++ b/src/lerobot/envs/configs.py
@@ -328,6 +328,7 @@ class LiberoEnv(EnvConfig):
     render_mode: str = "rgb_array"
     camera_name: str = "agentview_image,robot0_eye_in_hand_image"
     init_states: bool = True
+    hard_reset: bool = True
     camera_name_mapping: dict[str, str] | None = None
     observation_height: int = 360
     observation_width: int = 360
@@ -356,6 +357,8 @@ class LiberoEnv(EnvConfig):
     def __post_init__(self):
         if self.fps <= 0:
             raise ValueError(f"fps must be positive, got {self.fps}")
+        if not self.hard_reset and not self.init_states:
+            raise ValueError("hard_reset=False requires init_states=True")
 
         if self.obs_type == "pixels":
             self.features[LIBERO_KEY_PIXELS_AGENTVIEW] = PolicyFeature(
@@ -416,6 +419,7 @@ class LiberoEnv(EnvConfig):
             "observation_height": self.observation_height,
             "observation_width": self.observation_width,
             "control_freq": self.fps,
+            "hard_reset": self.hard_reset,
         }
         if self.task_ids is not None:
             kwargs["task_ids"] = self.task_ids
diff --git a/src/lerobot/envs/libero.py b/src/lerobot/envs/libero.py
index b959ca8fb..a3e0f17c4 100644
--- a/src/lerobot/envs/libero.py
+++ b/src/lerobot/envs/libero.py
@@ -128,10 +128,13 @@ class LiberoEnv(gym.Env):
         control_freq: int = 20,
         control_mode: str = "relative",
         is_libero_plus: bool = False,
+        hard_reset: bool = True,
     ):
         super().__init__()
         if control_freq <= 0:
             raise ValueError(f"control_freq must be positive, got {control_freq}")
+        if not hard_reset and not init_states:
+            raise ValueError("hard_reset=False requires init_states=True")
         self.task_id = task_id
         self.is_libero_plus = is_libero_plus
         self.obs_type = obs_type
@@ -158,6 +161,7 @@ class LiberoEnv(gym.Env):
         self.camera_name_mapping = camera_name_mapping
         self.num_steps_wait = num_steps_wait
         self.control_freq = control_freq
+        self.hard_reset = hard_reset
         self.episode_index = episode_index
         self.episode_length = episode_length
         # Load once and keep
@@ -265,6 +269,9 @@ class LiberoEnv(gym.Env):
             camera_heights=self.observation_height,
             camera_widths=self.observation_width,
             control_freq=self.control_freq,
+            # Soft resets skip LIBERO's model and renderer rebuild. They are opt-in
+            # because settle steps can make their observations differ from hard resets.
+            hard_reset=self.hard_reset,
         )
         env.reset()
         self._env = env