Langevin Dynamics For Adaptive Inverse Reinforcement Learning Of Stochastic Gradient Algorithms

Abstract

Inverse reinforcement learning (IRL) aims to estimate the reward function of optimizing agents by observing their response (estimates or actions). This paper considers IRL when noisy estimates of the gradient of a reward function generated by multiple stochastic gradient agents are observed. We present a generalized Langevin dynamics algorithm to estimate the reward function \(R(\theta)\); specifically, the resulting Langevin algorithm asymptotically generates samples from the distribution proportional to \(\exp(R(\theta))\). The proposed IRL algorithms use kernel-based passive learning schemes. We also construct multi-kernel passive Langevin algorithms for IRL which are suitable for high dimensional data. The performance of the proposed IRL algorithms are illustrated on examples in adaptive Bayesian learning, logistic regression (high dimensional problem) and constrained Markov decision processes. We prove weak convergence of the proposed IRL algorithms using martingale averaging meth

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykrishnamurthy2020langevin

Related papers

• Finite-sample Bounds For Adaptive Inverse Reinforcement Learning Using Passive Langevin Dynamics (2023)0.00
• Inverse Reinforcement Learning With Simultaneous Estimation Of Rewards And Dynamics (2016)0.00
• Towards Theoretical Understanding Of Inverse Reinforcement Learning (2023)0.00
• Inverse Reinforcement Learning Using Revealed Preferences And Passive Stochastic Optimization (2025)0.00
• Maximum-likelihood Inverse Reinforcement Learning With Finite-time Guarantees (2022)0.00
• Distributional Inverse Reinforcement Learning (2025)0.00
• In-trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates (2024)5.24
• Kernel Based Maximum Entropy Inverse Reinforcement Learning For Mean-field Games (2025)0.00