Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics

by   Michael Herman, et al.

Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to solve the inverse problem accurately. These assumptions are often not satisfied. To overcome this, we present a gradient-based IRL approach that simultaneously estimates the system's dynamics. By solving the combined optimization problem, our approach takes into account the bias of the demonstrations, which stems from the generating policy. The evaluation on a synthetic MDP and a transfer learning task shows improvements regarding the sample efficiency as well as the accuracy of the estimated reward functions and transition models.



page 7

page 13


Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning

While most approaches to the problem of Inverse Reinforcement Learning (...

Plug and Play, Model-Based Reinforcement Learning

Sample-efficient generalisation of reinforcement learning approaches hav...

Uniqueness and Complexity of Inverse MDP Models

What is the action sequence aa'a" that was likely responsible for reachi...

A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress

Inverse reinforcement learning is the problem of inferring the reward fu...

CWAE-IRL: Formulating a supervised approach to Inverse Reinforcement Learning problem

Inverse reinforcement learning (IRL) is used to infer the reward functio...

Langevin Dynamics for Inverse Reinforcement Learning of Stochastic Gradient Algorithms

Inverse reinforcement learning (IRL) aims to estimate the reward functio...

Inverse Reinforce Learning with Nonparametric Behavior Clustering

Inverse Reinforcement Learning (IRL) is the task of learning a single re...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.