AbideGym: Turning Static RL Worlds into Adaptive Challenges

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Aryan, Abi, Liu, Zac, Childress, Aaron
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916970329276416
author Aryan, Abi
Liu, Zac
Childress, Aaron
author_facet Aryan, Abi
Liu, Zac
Childress, Aaron
contents Agents trained with reinforcement learning often develop brittle policies that fail when dynamics shift, a problem amplified by static benchmarks. AbideGym, a dynamic MiniGrid wrapper, introduces agent-aware perturbations and scalable complexity to enforce intra-episode adaptation. By exposing weaknesses in static policies and promoting resilience, AbideGym provides a modular, reproducible evaluation framework for advancing research in curriculum learning, continual learning, and robust generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21234
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AbideGym: Turning Static RL Worlds into Adaptive Challenges
Aryan, Abi
Liu, Zac
Childress, Aaron
Machine Learning
Multiagent Systems
Agents trained with reinforcement learning often develop brittle policies that fail when dynamics shift, a problem amplified by static benchmarks. AbideGym, a dynamic MiniGrid wrapper, introduces agent-aware perturbations and scalable complexity to enforce intra-episode adaptation. By exposing weaknesses in static policies and promoting resilience, AbideGym provides a modular, reproducible evaluation framework for advancing research in curriculum learning, continual learning, and robust generalization.
title AbideGym: Turning Static RL Worlds into Adaptive Challenges
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2509.21234