paper-with-me

홈 › Papers

Benchmarking Constraint Inference in Inverse Reinforcement Learning

2022-06-20 · Guiliang Liu, Yudong Luo, Ashish Gaurav, Kasra Rezaee, Pascal Poupart

When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints are often hard to specify mathematically and unknown to the RL agents. To tackle these issues, Inverse Constrained Reinforcement Learning (ICRL) empirically estimates constraints from expert demonstrations. As an emerging research topic, ICRL does not have common benchmarks, and previous works tested algorithms under hand-crafted environments with manually-generated expert demonstrations. In this paper, we construct an ICRL benchmark in the context of RL application domains, including robot control, and autonomous driving. For each environment, we design relevant constraints and train expert agents to generate demonstration data. Besides, unlike existing baselines that learn a deterministic constraint, we propose a variational ICRL method to model a posterior distribution of candidate constraints. We conduct extensive experiments on these algorithms under our benchmark and show how they can facilitate studying important research challenges for ICRL. The benchmark, including the instructions for reproducing ICRL algorithms, is available at https://github.com/Guiliang/ICRL-benchmarks-public.

📄 PDF Abstract BibTeX arXiv:2206.09670

Code (2)

guiliang/cirl-benchmarks-public 공식 구현 pytorch
guiliang/icrl-benchmarks-public 공식 구현 pytorch

Tasks

Autonomous DrivingBenchmarkingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning

2024-09-24 · Bo Yue, Jian Li, Guiliang Liu

Optimizing objective functions subject to constraints is fundamental in many real-world applications. However, these constraints are often not readily defined and must be inferred from expert agent behaviors, a problem k…

Efficient Explorationreinforcement-learningReinforcement Learning

Efficient Inference for Inverse Reinforcement Learning and Dynamic Discrete Choice Models

2025-12-30 · Lars van der Laan, Aurelien Bibaut, Nathan Kallus arxiv

In many sequential decision-making problems, researchers observe actions but not the rewards that drive behavior, yet still wish to evaluate and compare counterfactual policies. Inverse reinforcement learning (IRL) and d…

Reinforcement Learning

Multi-Objective Constraint Inference using Inverse reinforcement learning

2026-05-07 · Syed Ihtesham Hussain Shah, Floris den Hengst, Aneta Lisowska, Annette ten Teije arxiv

Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observing expert demonstrations. However, existing approaches typically assu…

Computational EfficiencyReinforcement Learning

Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning

2019-09-12 · ICLR 2020 1 · Dexter R. R. Scobee, S. Shankar Sastry

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the c…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

X-MEN: Guaranteed XOR-Maximum Entropy Constrained Inverse Reinforcement Learning

2022-03-22 · Fan Ding, Yeiang Xue

Inverse Reinforcement Learning (IRL) is a powerful way of learning from demonstrations. In this paper, we address IRL problems with the availability of prior knowledge that optimal policies will never violate certain con…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)