fix: close envs between tasks to prevent worker process accumulation

eval_policy_all never closed environments after each task completed,
causing AsyncVectorEnv worker processes to accumulate (N_tasks × n_envs).
This led to OOM, BrokenPipeError and EOFError on multi-task benchmarks.

Also fixes:
- AsyncVectorEnv compat in envs/utils.py (use get_attr/call instead of .envs)
- Tuple task handling in tokenizer_processor and lerobot_eval
- _LazyAsyncVectorEnv for deferred worker spawning in LIBERO

Made-with: Cursor

src/lerobot/processor/tokenizer_processor.py

@@ -136,8 +136,8 @@ class TokenizerProcessorStep(ObservationProcessorStep):
         # Standardize to a list of strings for the tokenizer
         if isinstance(task, str):
             return [task]
-        elif isinstance(task, list) and all(isinstance(t, str) for t in task):
-            return task
+        elif isinstance(task, (list, tuple)) and all(isinstance(t, str) for t in task):
+            return list(task)
 
         return None