{"ID":2879931,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.15693","arxiv_id":"2508.15693","title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","abstract":"We present NiceWebRL, a research tool that enables researchers to use machine reinforcement learning (RL) environments for online human subject experiments. NiceWebRL is a Python library that allows any Jax-based environment to be transformed into an online interface, supporting both single-agent and multi-agent environments. As such, NiceWebRL enables AI researchers to compare their algorithms to human performance, cognitive scientists to test ML algorithms as theories for human cognition, and multi-agent researchers to develop algorithms for human-AI collaboration. We showcase NiceWebRL with 3 case studies that demonstrate its potential to help develop Human-like AI, Human-compatible AI, and Human-assistive AI. In the first case study (Human-like AI), NiceWebRL enables the development of a novel RL model of cognition. Here, NiceWebRL facilitates testing this model against human participants in both a grid world and Craftax, a 2D Minecraft domain. In our second case study (Human-compatible AI), NiceWebRL enables the development of a novel multi-agent RL algorithm that can generalize to human partners in the Overcooked domain. Finally, in our third case study (Human-assistive AI), we show how NiceWebRL can allow researchers to study how an LLM can assist humans on complex tasks in XLand-Minigrid, an environment with millions of hierarchical tasks. The library is available at https://github.com/KempnerInstitute/nicewebrl.","short_abstract":"We present NiceWebRL, a research tool that enables researchers to use machine reinforcement learning (RL) environments for online human subject experiments. NiceWebRL is a Python library that allows any Jax-based environment to be transformed into an online interface, supporting both single-agent and multi-agent enviro...","url_abs":"https://arxiv.org/abs/2508.15693","url_pdf":"https://arxiv.org/pdf/2508.15693v1","authors":"[\"Wilka Carvalho\",\"Vikram Goddla\",\"Ishaan Sinha\",\"Hoon Shin\",\"Kunal Jha\"]","published":"2025-08-21T16:18:49Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false,"code_links":[{"ID":610642,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2879931,"paper_url":"https://arxiv.org/abs/2508.15693","paper_title":"NiceWebRL: a Python library for human subject experiments with reinforcement learning environments","repo_url":"https://github.com/KempnerInstitute/nicewebrl","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}