@inproceedings{Harish_Reinforcement_2024,
	title={{Reinforcement} {Learning} {via} {Auxiliary} {Task} {Distillation}},
	author={Harish, Abhinav Narayan and Heck, Larry and Hanna, Josiah P. and Kira, Zsolt and Szot, Andrew},
	year={2024},
	month={October},
	booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
	abstract={
		We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems by distilling behaviors from auxiliary RL tasks. AuxDistill achieves this by concurrently carrying out multi-task RL with auxiliary tasks, which are easier to learn and relevant to the main task. A weighted distillation loss transfers behaviors from these auxiliary tasks to solve the main task. We demonstrate that AuxDistill can learn a pixels-to-actions policy for a challenging multi-stage embodied object rearrangement task from the environment reward without demonstrations, a learning curriculum, or pre-trained skills. AuxDistill achieves $2.3 \times$ higher success than the previous state-of-the-art baseline in the Habitat Object Rearrangement benchmark and outperforms methods that use pre-trained skills and expert demonstrations.
	},
}