PHYSICS-REGULATED DEEP REINFORCEMENT LEARNING: INVARIANT EMBEDDINGS

Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo

Research output: Contribution to conferencePaperpeer-review

Abstract

This paper proposes the Phy-DRL: a physics-regulated deep reinforcement learning (DRL) framework for safety-critical autonomous systems. The Phy-DRL has three distinguished invariant-embedding designs: i) residual action policy (i.e., integrating data-driven-DRL action policy and physics-model-based action policy), ii) automatically constructed safety-embedded reward, and iii) physics-model-guided neural network (NN) editing, including link editing and activation editing. Theoretically, the Phy-DRL exhibits 1) a mathematically provable safety guarantee and 2) strict compliance of critic and actor networks with physics knowledge about the action-value function and action policy. Finally, we evaluate the Phy-DRL on a cart-pole system and a quadruped robot. The experiments validate our theoretical results and demonstrate that Phy-DRL features guaranteed safety compared to purely data-driven DRL and solely model-based design while offering remarkably fewer learning parameters and fast training towards safety guarantee.

Original languageEnglish
StatePublished - 2024
Event12th International Conference on Learning Representations, ICLR 2024 - Hybrid, Vienna, Austria
Duration: 7 May 202411 May 2024

Conference

Conference12th International Conference on Learning Representations, ICLR 2024
Country/TerritoryAustria
CityHybrid, Vienna
Period7/05/2411/05/24

Fingerprint

Dive into the research topics of 'PHYSICS-REGULATED DEEP REINFORCEMENT LEARNING: INVARIANT EMBEDDINGS'. Together they form a unique fingerprint.

Cite this