Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Lili, Evans, Ben, Islam, Riashat, Seraj, Raihan, Efroni, Yonathan, Lamb, Alex
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914765590233088
author Wu, Lili
Evans, Ben
Islam, Riashat
Seraj, Raihan
Efroni, Yonathan
Lamb, Alex
author_facet Wu, Lili
Evans, Ben
Islam, Riashat
Seraj, Raihan
Efroni, Yonathan
Lamb, Alex
contents Discovering an informative, or agent-centric, state representation that encodes only the relevant information while discarding the irrelevant is a key challenge towards scaling reinforcement learning algorithms and efficiently applying them to downstream tasks. Prior works studied this problem in high-dimensional Markovian environments, when the current observation may be a complex object but is sufficient to decode the informative state. In this work, we consider the problem of discovering the agent-centric state in the more challenging high-dimensional non-Markovian setting, when the state can be decoded from a sequence of past observations. We establish that generalized inverse models can be adapted for learning agent-centric state representation for this task. Our results include asymptotic theory in the deterministic dynamics setting as well as counter-examples for alternative intuitive algorithms. We complement these findings with a thorough empirical study on the agent-centric state discovery abilities of the different alternatives we put forward. Particularly notable is our analysis of past actions, where we show that these can be a double-edged sword: making the algorithms more successful when used correctly and causing dramatic failure when used incorrectly.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14552
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs
Wu, Lili
Evans, Ben
Islam, Riashat
Seraj, Raihan
Efroni, Yonathan
Lamb, Alex
Machine Learning
Artificial Intelligence
Discovering an informative, or agent-centric, state representation that encodes only the relevant information while discarding the irrelevant is a key challenge towards scaling reinforcement learning algorithms and efficiently applying them to downstream tasks. Prior works studied this problem in high-dimensional Markovian environments, when the current observation may be a complex object but is sufficient to decode the informative state. In this work, we consider the problem of discovering the agent-centric state in the more challenging high-dimensional non-Markovian setting, when the state can be decoded from a sequence of past observations. We establish that generalized inverse models can be adapted for learning agent-centric state representation for this task. Our results include asymptotic theory in the deterministic dynamics setting as well as counter-examples for alternative intuitive algorithms. We complement these findings with a thorough empirical study on the agent-centric state discovery abilities of the different alternatives we put forward. Particularly notable is our analysis of past actions, where we show that these can be a double-edged sword: making the algorithms more successful when used correctly and causing dramatic failure when used incorrectly.
title Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2404.14552