# AbideGym: Turning Static RL Worlds into Adaptive Challenges

arXiv: https://arxiv.org/abs/2509.21234 · HTML: https://mlsanity.com/paper/2509.21234/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 29 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 26 of 26)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Automatic Curriculum Learning For Deep RL: A Short Survey](https://mlsanity.com/paper/2003.04664/) (2020)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Continual World: A Robotic Benchmark For Continual Reinforcement Learning](https://mlsanity.com/paper/2105.10919/) (2021)
- [Self-Evolving Curriculum for LLM Reasoning](https://mlsanity.com/paper/2505.14970/) (2025)
- [Efficient Reinforcement Finetuning via Adaptive Curriculum Learning](https://mlsanity.com/paper/2504.05520/) (2025)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation](https://mlsanity.com/paper/1806.10729/) (2018)
- [Adversarial Reinforcement Learning for Procedural Content Generation](https://mlsanity.com/paper/2103.04847/) (2021)
- [The Generalization Gap in Offline Reinforcement Learning](https://mlsanity.com/paper/2312.05742/) (2023)
- [On Generalization Across Environments In Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2503.00799/) (2025)
- [Deep Reinforcement Learning Agents are not even close to Human Intelligence](https://mlsanity.com/paper/2505.21731/) (2025)
- [Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay](https://mlsanity.com/paper/2411.10809/) (2024)
- [Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale](https://mlsanity.com/paper/2410.10905/) (2024)
- [Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence](https://mlsanity.com/paper/2402.02701/) (2024)
- [Continual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognition](https://mlsanity.com/paper/2505.09003/) (2025)
- [Continual Visual Reinforcement Learning with A Life-Long World Model](https://mlsanity.com/paper/2303.06572/) (2023)
- [Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments](https://mlsanity.com/paper/2507.13846/) (2025)
- [A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks](https://mlsanity.com/paper/2506.02883/) (2025)
- [Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation](https://mlsanity.com/paper/2508.09860/) (2025)
- [Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor](https://mlsanity.com/paper/2501.18490/) (2025)
- [Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces](https://mlsanity.com/paper/2506.05702/) (2025)
- [Causal Reflection with Language Models](https://mlsanity.com/paper/2508.04495/) (2025)

## Built on by (most cited first, 1 of 1)

- [Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL](https://mlsanity.com/paper/2607.16204/) (2026)

## Abstract (arXiv)

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.