{"ID":2866069,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21234","arxiv_id":"2509.21234","title":"AbideGym: Turning Static RL Worlds into Adaptive Challenges","abstract":"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.","short_abstract":"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 poli...","url_abs":"https://arxiv.org/abs/2509.21234","url_pdf":"https://arxiv.org/pdf/2509.21234v1","authors":"[\"Abi Aryan\",\"Zac Liu\",\"Aaron Childress\"]","published":"2025-09-25T14:34:36Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.MA\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}