A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimization

05/17/2023
by   Akira Kitaoka, et al.
0

We prove Wasserstein inverse reinforcement learning enables the learner's reward values to imitate the expert's reward values in a finite iteration for multi-objective optimizations. Moreover, we prove Wasserstein inverse reinforcement learning enables the learner's optimal solutions to imitate the expert's optimal solutions for multi-objective optimizations with lexicographic order.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/10/2023

A proof of convergence of inverse reinforcement learning for multi-objective optimization

We show the convergence of Wasserstein inverse reinforcement learning fo...
research
10/07/2020

Regularized Inverse Reinforcement Learning

Inverse Reinforcement Learning (IRL) aims to facilitate a learner's abil...
research
04/01/2022

Automating Staged Rollout with Reinforcement Learning

Staged rollout is a strategy of incrementally releasing software updates...
research
07/19/2017

Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning

Reinforcement learning is widely used for dialogue policy optimization w...
research
10/20/2022

Robust Imitation via Mirror Descent Inverse Reinforcement Learning

Recently, adversarial imitation learning has shown a scalable reward acq...
research
01/05/2023

Data-Driven Inverse Reinforcement Learning for Expert-Learner Zero-Sum Games

In this paper, we formulate inverse reinforcement learning (IRL) as an e...

Please sign up or login with your details

Forgot password? Click here to reset