3 Commits

Author	SHA1	Message	Date
Pepijn Kooijmans	1f7e7b4a90	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	2026-04-07 12:30:22 +02:00
Pepijn	8ed658c6aa	fix(tests): fix 3 failing dispatch tests ... - test_registry_all_types: skip non-EnvConfig stubs (e.g. TestPluginConfig) - test_processors_delegation: use None instead of abstract PreTrainedConfig - test_custom_get_env_processors_override: use DataProcessorPipeline for isinstance check (PolicyProcessorPipeline is a subscripted generic) Made-with: Cursor	2026-04-03 17:19:27 +02:00
Pepijn	24d9b74d81	refactor(envs): move dispatch logic from factory into EnvConfig subclasses ... Replace hardcoded if/elif chains in factory.py with create_envs() and get_env_processors() methods on EnvConfig. New benchmarks now only need to register a config subclass — no factory.py edits required. Net -23 lines: factory.py shrinks from ~200 to ~70 lines of logic. Made-with: Cursor	2026-04-03 13:23:44 +02:00