WAALiveAdapter._get_observation() does not populate raw_observation with the task instruction. RLEnvironment stores _current_task.instruction but never exposes it on observations.
This means RL agents using observations cannot see what task they should perform.
Fix: populate raw_observation["instruction"] in observe(), or add a public current_instruction property to RLEnvironment.
WAALiveAdapter._get_observation()does not populateraw_observationwith the task instruction.RLEnvironmentstores_current_task.instructionbut never exposes it on observations.This means RL agents using observations cannot see what task they should perform.
Fix: populate
raw_observation["instruction"]inobserve(), or add a publiccurrent_instructionproperty toRLEnvironment.