paper-with-me

홈 › Papers

Inverse Constrained Reinforcement Learning

2020-11-19 · Usman Anwar, Shehryar Malik, Alireza Aghasi, Ali Ahmed

In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely. In this work, we consider the problem of learning constraints from demonstrations of a constraint-abiding agent's behavior. We experimentally validate our approach and show that our framework can successfully learn the most likely constraints that the agent respects. We further show that these learned constraints are \textit{transferable} to new agents that may have different morphologies and/or reward functions. Previous works in this regard have either mainly been restricted to tabular (discrete) settings, specific types of constraints or assume the environment's transition dynamics. In contrast, our framework is able to learn arbitrary \textit{Markovian} constraints in high-dimensions in a completely model-free setting. The code can be found it: \url{https://github.com/shehryar-malik/icrl}.

📄 PDF Abstract BibTeX arXiv:2011.09999

Code (1)

shehryar-malik/icrl 공식 구현 pytorch

Tasks

reinforcement-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

Inverse Reinforcement Learning With Constraint Recovery

2023-05-14 · Nirjhar Das, Arpan Chattopadhyay

In this work, we propose a novel inverse reinforcement learning (IRL) algorithm for constrained Markov decision process (CMDP) problems. In standard IRL problems, the inverse learner or agent seeks to recover the reward …

reinforcement-learningReinforcement Learning

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)

Identifiability and Generalizability in Constrained Inverse Reinforcement Learning

2023-06-01 · Andreas Schlaginhaufen, Maryam Kamgarpour

Two main challenges in Reinforcement Learning (RL) are designing appropriate reward functions and ensuring the safety of the learned policy. To address these challenges, we present a theoretical framework for Inverse Rei…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory

2024-05-29 · Mustafa Mert Çelikok, Frans A. Oliehoek, Jan-Willem van de Meent

We consider inverse reinforcement learning problems with concave utilities. Concave Utility Reinforcement Learning (CURL) is a generalisation of the standard RL objective, which employs a concave function of the state oc…

Imitation LearningOffline RLreinforcement-learningReinforcement Learning

Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations

2023-09-21 · NeurIPS 2023 11

Inverse Constraint Reinforcement Learning (ICRL) aims to recover the underlying constraints respected by expert agents in a data-driven manner. Existing ICRL algorithms typically assume that the demonstration data is gen…