Saved in:
Bibliographic Details
Main Authors: Bajgar, Ondrej, Abate, Alessandro, Gatsis, Konstantinos, Osborne, Michael A.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.10971
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916324796530688
author Bajgar, Ondrej
Abate, Alessandro
Gatsis, Konstantinos
Osborne, Michael A.
author_facet Bajgar, Ondrej
Abate, Alessandro
Gatsis, Konstantinos
Osborne, Michael A.
contents The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a reward unknown to the learner. The resulting posterior over rewards can then be used to synthesize an apprentice policy that performs well on the same or a similar task. A key challenge in Bayesian IRL is bridging the computational gap between the hypothesis space of possible rewards and the likelihood, often defined in terms of Q values: vanilla Bayesian IRL needs to solve the costly forward planning problem - going from rewards to the Q values - at every step of the algorithm, which may need to be done thousands of times. We propose to solve this by a simple change: instead of focusing on primarily sampling in the space of rewards, we can focus on primarily working in the space of Q-values, since the computation required to go from Q-values to reward is radically cheaper. Furthermore, this reversion of the computation makes it easy to compute the gradient allowing efficient sampling using Hamiltonian Monte Carlo. We propose ValueWalk - a new Markov chain Monte Carlo method based on this insight - and illustrate its advantages on several tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10971
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Walking the Values in Bayesian Inverse Reinforcement Learning
Bajgar, Ondrej
Abate, Alessandro
Gatsis, Konstantinos
Osborne, Michael A.
Machine Learning
The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a reward unknown to the learner. The resulting posterior over rewards can then be used to synthesize an apprentice policy that performs well on the same or a similar task. A key challenge in Bayesian IRL is bridging the computational gap between the hypothesis space of possible rewards and the likelihood, often defined in terms of Q values: vanilla Bayesian IRL needs to solve the costly forward planning problem - going from rewards to the Q values - at every step of the algorithm, which may need to be done thousands of times. We propose to solve this by a simple change: instead of focusing on primarily sampling in the space of rewards, we can focus on primarily working in the space of Q-values, since the computation required to go from Q-values to reward is radically cheaper. Furthermore, this reversion of the computation makes it easy to compute the gradient allowing efficient sampling using Hamiltonian Monte Carlo. We propose ValueWalk - a new Markov chain Monte Carlo method based on this insight - and illustrate its advantages on several tasks.
title Walking the Values in Bayesian Inverse Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2407.10971