Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning

Yuxiao Lu, Arunesh Sinha, Pradeep Varakantham

Research output: Contribution to journalConference articlepeer-review

Abstract

Safety in goal directed Reinforcement Learning (RL) settings has typically been handled through constraints over trajectories and have demonstrated good performance in primarily short horizon tasks. In this paper, we are specifically interested in the problem of solving temporally extended decision making problems such as robots cleaning different areas in a house while avoiding slippery and unsafe areas (e.g., stairs) and retaining enough charge to move to a charging dock; in the presence of complex safety constraints. Our key contribution is a (safety) Constrained Search with Hierarchical Reinforcement Learning (CoSHRL) mechanism that combines an upper level constrained search agent (which computes a reward maximizing policy from a given start to a far away goal state while satisfying cost constraints) with a low-level goal conditioned RL agent (which estimates cost and reward values to move between nearby states). A major advantage of CoSHRL is that it can handle constraints on the cost value distribution (e.g., on Conditional Value at Risk, CVaR) and can adjust to flexible constraint thresholds without retraining. We perform extensive experiments with different types of safety constraints to demonstrate the utility of our approach over leading approaches in constrained and hierarchical RL.

Original languageEnglish (US)
Pages (from-to)21368-21377
Number of pages10
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume38
Issue number19
DOIs
StatePublished - Mar 25 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: Feb 20 2024Feb 27 2024

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning'. Together they form a unique fingerprint.

Cite this