Abstract
In this work, we introduce PIPER: Primitive-Informed Preference-based Hierarchical reinforcement learning via Hindsight Relabeling, a novel approach that leverages preference-based learning to learn a reward model, and subsequently uses this reward model to relabel higher-level replay buffers. Since this reward is unaffected by lower primitive behavior, our relabeling-based approach is able to mitigate non-stationarity, which is common in existing hierarchical approaches, and demonstrates impressive performance across a range of challenging sparse-reward tasks. Since obtaining human feedback is typically impractical, we propose to replace the human-in-the-loop approach with our primitive-in-the-loop approach, which generates feedback using sparse rewards provided by the environment. Moreover, in order to prevent infeasible subgoal prediction and avoid degenerate solutions, we propose primitive-informed regularization that conditions higher-level policies to generate feasible subgoals for lower-level policies. We perform extensive experiments to show that PIPER mitigates non-stationarity in hierarchical reinforcement learning and achieves greater than 50% success rates in challenging, sparse-reward robotic environments, where most other baselines fail to achieve any significant progress.
Original language | English |
---|---|
Pages (from-to) | 45681-45695 |
Number of pages | 15 |
Journal | Proceedings of Machine Learning Research |
Volume | 235 |
Publication status | Published - 27 Jul 2024 |
Event | 41st International Conference on Machine Learning, ICML 2024 - Vienna, Austria Duration: 21 Jul 2024 → 27 Jul 2024 |
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability