paper-with-me

Papers

Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning using Passive Langevin Dynamics

2023-04-18 · Luke Snow, Vikram Krishnamurthy

This paper provides a finite-sample analysis of a passive stochastic gradient Langevin dynamics (PSGLD) algorithm. This algorithm is designed to achieve adaptive inverse reinforcement learning (IRL). Adaptive IRL aims to estimate the cost function of a forward learner performing a stochastic gradient algorithm (e.g., policy gradient reinforcement learning) by observing their estimates in real-time. The PSGLD algorithm is considered passive because it incorporates noisy gradients provided by an external stochastic gradient algorithm (forward learner), of which it has no control. The PSGLD algorithm acts as a randomized sampler to achieve adaptive IRL by reconstructing the forward learner's cost function nonparametrically from the stationary measure of a Langevin diffusion. This paper analyzes the non-asymptotic (finite-sample) performance; we provide explicit bounds on the 2-Wasserstein distance between PSGLD algorithm sample measure and the stationary measure encoding the cost function, and provide guarantees for a kernel density estimation scheme which reconstructs the cost function from empirical samples. Our analysis uses tools from the study of Markov diffusion operators. The derived bounds have both practical and theoretical significance. They provide finite-time guarantees for an adaptive IRL mechanism, and substantially generalize the analytical framework of a line of research in passive stochastic gradient algorithms.

📄 PDF Abstract BibTeX arXiv:2304.09123

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimationreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces

2024-05-24 · Angeliki Kamoutsi, Peter Schmitt-Förster, Tobias Sutter, Volkan Cevher 외

This work studies discrete-time discounted Markov decision processes with continuous state and action spaces and addresses the inverse problem of inferring a cost function from observed optimal behavior. We first conside…

Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problems

2020-07-07 · Kunal Pattanayak, Vikram Krishnamurthy

This paper presents an inverse reinforcement learning~(IRL) framework for Bayesian stopping time problems. By observing the actions of a Bayesian decision maker, we provide a necessary and sufficient condition to identif…

reinforcement-learningReinforcement Learning (RL)Two-sample testing

Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach

2026-05-27 · Guang-Yuan Hao, Lars van der Laan, Aurélien Bibaut, Nathan Kallus arxiv

We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environment. This arises naturally when demonstrat…

Reinforcement Learning

Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning

2019-07-14 · NeurIPS 2019 12 · Harsh Gupta, R. Srikant, Lei Ying

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the ca…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning

2017-07-03 · Daniel S. Brown, Scott Niekum

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)