fix: critic called once (was 3x), adaptive KL schedule restored, upgrade 3m

2026-07-01 15:05:50 +08:00
parent ef3ccb2e1a
commit 3038aa7ac7
6 changed files with 149 additions and 9 deletions
--- a/scripts/dreamwaq_sim2sim_mujoco.py
+++ b/scripts/dreamwaq_sim2sim_mujoco.py
@@ -235,8 +235,8 @@ def main():

            # ONNX inference
            outputs = session.run(None, {
-                'observations': obs.reshape(1, -1).astype(np.float32),
-                'obs_history': history.astype(np.float32),
+                'obs': obs.reshape(1, -1).astype(np.float32),
+                'obs_history': history.reshape(1, -1).astype(np.float32),
            })
            action = outputs[0][0]
            action = np.clip(action, -CLIP_ACTIONS, CLIP_ACTIONS)