paper-with-me

홈 › Papers

On the Correctness and Sample Complexity of Inverse Reinforcement Learning

2019-06-02 · NeurIPS 2019 12 · Abi Komanduru, Jean Honorio

Inverse reinforcement learning (IRL) is the problem of finding a reward function that generates a given optimal policy for a given Markov Decision Process. This paper looks at an algorithmic-independent geometric analysis of the IRL problem with finite states and actions. A L1-regularized Support Vector Machine formulation of the IRL problem motivated by the geometric analysis is then proposed with the basic objective of the inverse reinforcement problem in mind: to find a reward function that generates a specified optimal policy. The paper further analyzes the proposed formulation of inverse reinforcement learning with $n$ states and $k$ actions, and shows a sample complexity of $O(n^2 \log (nk))$ for recovering a reward function that generates a policy that satisfies Bellman's optimality condition with respect to the true transition probabilities.

📄 PDF Abstract BibTeX arXiv:1906.00422

Code (1)

akomandu/L1SVMIRL 공식 구현

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees

2021-02-16 · NeurIPS 2021 12 · Gregory Dexter, Kevin Bello, Jean Honorio

Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. The IRL setting is remarkably useful for automated control, in situations where the reward …

reinforcement-learningReinforcement Learning (RL)

Sample Efficient Social Navigation Using Inverse Reinforcement Learning

2021-06-18 · Bobak H. Baghi, Gregory Dudek

In this paper, we present an algorithm to efficiently learn socially-compliant navigation policies from observations of human trajectories. As mobile robots come to inhabit and traffic social spaces, they must account fo…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Social Navigation

A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning

2021-03-07 · Abi Komanduru, Jean Honorio

Inverse reinforcement learning (IRL) is the task of finding a reward function that generates a desired optimal policy for a given Markov Decision Process (MDP). This paper develops an information-theoretic lower bound fo…

reinforcement-learningReinforcement Learning (RL)

Active Exploration for Inverse Reinforcement Learning

2022-07-18 · David Lindner, Andreas Krause, Giorgia Ramponi

Inverse Reinforcement Learning (IRL) is a powerful paradigm for inferring a reward function from expert demonstrations. Many IRL algorithms require a known transition model and sometimes even a known expert policy, or th…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Statistical analysis of Inverse Entropy-regularized Reinforcement Learning

2025-12-07 · Denis Belomestny, Alexey Naumov, Sergey Samsonov arxiv

Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs. A long-standing difficulty in classical IRL is the non-uniqueness of th…

Reinforcement Learning