Saved in:
Bibliographic Details
Main Authors: Ke, Jingyang, Wu, Feiyang, Wang, Jiyi, Markowitz, Jeffrey, Wu, Anqi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.12633
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916844247449600
author Ke, Jingyang
Wu, Feiyang
Wang, Jiyi
Markowitz, Jeffrey
Wu, Anqi
author_facet Ke, Jingyang
Wu, Feiyang
Wang, Jiyi
Markowitz, Jeffrey
Wu, Anqi
contents Traditional approaches to studying decision-making in neuroscience focus on simplified behavioral tasks where animals perform repetitive, stereotyped actions to receive explicit rewards. While informative, these methods constrain our understanding of decision-making to short timescale behaviors driven by explicit goals. In natural environments, animals exhibit more complex, long-term behaviors driven by intrinsic motivations that are often unobservable. Recent works in time-varying inverse reinforcement learning (IRL) aim to capture shifting motivations in long-term, freely moving behaviors. However, a crucial challenge remains: animals make decisions based on their history, not just their current state. To address this, we introduce SWIRL (SWitching IRL), a novel framework that extends traditional IRL by incorporating time-varying, history-dependent reward functions. SWIRL models long behavioral sequences as transitions between short-term decision-making processes, each governed by a unique reward function. SWIRL incorporates biologically plausible history dependency to capture how past decisions and environmental contexts shape behavior, offering a more accurate description of animal decision-making. We apply SWIRL to simulated and real-world animal behavior datasets and show that it outperforms models lacking history dependency, both quantitatively and qualitatively. This work presents the first IRL model to incorporate history-dependent policies and rewards to advance our understanding of complex, naturalistic decision-making in animals.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12633
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
Ke, Jingyang
Wu, Feiyang
Wang, Jiyi
Markowitz, Jeffrey
Wu, Anqi
Machine Learning
Artificial Intelligence
Traditional approaches to studying decision-making in neuroscience focus on simplified behavioral tasks where animals perform repetitive, stereotyped actions to receive explicit rewards. While informative, these methods constrain our understanding of decision-making to short timescale behaviors driven by explicit goals. In natural environments, animals exhibit more complex, long-term behaviors driven by intrinsic motivations that are often unobservable. Recent works in time-varying inverse reinforcement learning (IRL) aim to capture shifting motivations in long-term, freely moving behaviors. However, a crucial challenge remains: animals make decisions based on their history, not just their current state. To address this, we introduce SWIRL (SWitching IRL), a novel framework that extends traditional IRL by incorporating time-varying, history-dependent reward functions. SWIRL models long behavioral sequences as transitions between short-term decision-making processes, each governed by a unique reward function. SWIRL incorporates biologically plausible history dependency to capture how past decisions and environmental contexts shape behavior, offering a more accurate description of animal decision-making. We apply SWIRL to simulated and real-world animal behavior datasets and show that it outperforms models lacking history dependency, both quantitatively and qualitatively. This work presents the first IRL model to incorporate history-dependent policies and rewards to advance our understanding of complex, naturalistic decision-making in animals.
title Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.12633