mlsanityData to 14 Oct 2026

AbideGym: Turning Static RL Worlds into Adaptive Challenges

arXiv 2509.21234 ↗First posted 25 Sep 2025cs.LG cs.MAcited by 1

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

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.

Key facts. Cited by 1 paper 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.

Builds on

26 of 29 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Deep Reinforcement Learning Agents are not even close to Human Intelligence27 May
  2. 2025Continual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognition13 May
  3. 2024Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay16 Nov
  4. 2024Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale13 Oct
  5. 2024Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence5 Feb

Other references · 21

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  4. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  5. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 150
  6. 2018Assessing Generalization in Deep Reinforcement Learningcited by 133
  7. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 116
  8. 2025Self-Evolving Curriculum for LLM Reasoningcited by 112
  9. 2025Efficient Reinforcement Finetuning via Adaptive Curriculum Learningcited by 93
  10. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  11. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 81
  12. 2021Adversarial Reinforcement Learning for Procedural Content Generationcited by 36
9 more
  1. 2023The Generalization Gap in Offline Reinforcement Learningcited by 26
  2. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learningcited by 8
  3. 2023Continual Visual Reinforcement Learning with A Life-Long World Modelcited by 3
  4. 2025Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environmentscited by 3
  5. 2025A Continual Offline Reinforcement Learning Benchmark for Navigation Taskscited by 2
  6. 2025Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representationcited by 2
  7. 2025Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotorcited by 1
  8. 2025Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spacescited by 1
  9. 2025Causal Reflection with Language Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RLcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
  2. 2025ADAGE: A generic two-layer framework for adaptive agent based modelling
  3. 2025Scaling Agent Learning via Experience Synthesis
  4. 2026ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
  5. 2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
  6. 2026EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
  7. 2026ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
  8. 2026HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems