diff --git a/README.md b/README.md
index 441ddd6..0e595f1 100755
--- a/README.md
+++ b/README.md
@@ -14,7 +14,7 @@ Official implementation of
 
 **Announcement: training just got ~4.5x faster!**
 
-Expect **~4.5x** faster wall-time (depending on hardware and task) with the most recent release (Nov 10, 2024). A majority of the speedups in this branch are enabled with the additional flag `compile=true`. To run the code with `compile=true`, **you will need to install the latest `nightly` versions of PyTorch, TensorDict, and TorchRL**. See `docker/environment.yaml` for a tested configuration. `compile=true` is available in state-based online RL at the moment, and we expect to roll out support across all settings in the coming months. Thank you to [Vincent Moens](https://github.com/vmoens) who has been a key contributor to our torch.compile compatibility!
+Expect **~4.5x** faster wall-time (depending on hardware and task) with the most recent release (Nov 10, 2024). A majority of the speedups in this branch are enabled with the additional flag `compile=true`. To run the code with `compile=true`, **you will need to install recent `nightly` versions of PyTorch, TensorDict, and TorchRL**. See `docker/environment.yaml` for a tested configuration. Thank you to [Vincent Moens](https://github.com/vmoens) who has been a key contributor to our torch.compile compatibility!
 
 ----
 
diff --git a/tdmpc2/common/parser.py b/tdmpc2/common/parser.py
index e162eac..a8d9f25 100755
--- a/tdmpc2/common/parser.py
+++ b/tdmpc2/common/parser.py
@@ -77,9 +77,4 @@ def parse_cfg(cfg: OmegaConf) -> OmegaConf:
 		cfg.task_dim = 0
 	cfg.tasks = TASK_SET.get(cfg.task, [cfg.task])
 
-	# Check torch.compile compatibility
-	if cfg.get('compile', False):
-		assert cfg.obs == 'state', 'torch.compile only supports state observations at the moment.'
-		assert not cfg.multitask, 'torch.compile does not support multitask training at the moment.'
-
 	return cfg_to_dataclass(cfg)