Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples (2407.03311v2)

Abstract: Learning from examples of success is an ap pealing approach to reinforcement learning but it presents a challenging exploration problem, especially for complex or long-horizon tasks. This work introduces value-penalized auxiliary control from examples (VPACE), an algorithm that significantly improves exploration in example-based control by adding examples of simple auxiliary tasks. For instance, a manipulation task may have auxiliary examples of an object being reached for, grasped, or lifted. We show that the na\"{i}ve application of scheduled auxiliary control to example-based learning can lead to value overestimation and poor performance. We resolve the problem with an above-success-level value penalty. Across both simulated and real robotic environments, we show that our approach substantially improves learning efficiency for challenging tasks, while maintaining bounded value estimates. We compare with existing approaches to example-based learning, inverse reinforcement learning, and an exploration bonus. Preliminary results also suggest that VPACE may learn more efficiently than the more common approaches of using full trajectories or true sparse rewards. Videos, code, and datasets: https://papers.starslab.ca/vpace.