Research map / Reinforcement learning / Imitation learning

Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning

ICLR 2025 · Reinforcement learning › Imitation learning · approach: Theory of inverse RL

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Analyzes constraint inference in inverse constrained reinforcement learning (ICRL), which is typically cast as a tri-level optimization, to understand and simplify the constraint learning problem.

Problem

Inferring unknown safety constraints from expert demonstrations in inverse constrained reinforcement learning, which is typically formulated as a complex tri-level optimization problem.

Approach

Examines the ICRL constraint-inference problem analytically, motivated by the inherent complexity of its tri-level optimization structure, to better understand and address it. Details beyond the abstract are unavailable.

Experimental setup

Builds on: inverse constrained reinforcement learning

Closest papers by meaning

• Provably Efficient Exploration in Inverse Constrained Reinforcement Learning (ICML 2025 · similarity 0.93)
• Robust Inverse Constrained Reinforcement Learning under Model Misspecification (ICML 2024 · similarity 0.93)
• Simplifying Constraint Inference with Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.92)
• Recent Advancements in Inverse Reinforcement Learning (AAAI 2024 · similarity 0.92)
• Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective (ICML 2024 · similarity 0.92)
• Learning Constraints from Offline Demonstrations via Superior Distribution Correction Estimation (ICML 2024 · similarity 0.91)