Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach
Authors: Haitong Ma, Haoran Yu, Haobo Fu, Shuai Li
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our approach on a benchmark built upon the Overcooked environment a standard environment for human-agent collaboration and demonstrate remarkable performance across diverse preference styles and cooperative scenarios. Section 5 presents "Experiments" where the approach is evaluated against baselines using various metrics. |
| Researcher Affiliation | Collaboration | Haitong Ma Shanghai Jiao Tong University Shanghai Innovation Institute Shanghai, China EMAIL ... Haobo Fu Tencent AI Lab Shenzhen, China EMAIL |
| Pseudocode | Yes | Algorithm 1 Epoch-wise alternation recovery |
| Open Source Code | No | We will consider releasing our code with the camera-ready version. |
| Open Datasets | No | For the offline datasets, we collect trajectories across two layouts and three preference styles, with the number of trajectories for each combination summarized in Table 7. |
| Dataset Splits | Yes | For each layout-style pair, we split the trajectories into training and test sets using a 4:1 ratio. |
| Hardware Specification | Yes | All experiments were conducted on a single NVIDIA GeForce RTX 2080 Ti GPU. |
| Software Dependencies | No | The paper mentions using a CNN-MLP based architecture and MAPPO as the underlying reinforcement learning algorithm, but does not provide specific software versions for libraries, programming languages, or other dependencies. |
| Experiment Setup | Yes | C Hyper parameters In this section, we present the hyperparameters used and compute resources in our experiments. ... Table 8: Hyperparameters of self-play process ... Table 9: Hyperparameters of pretraining, online recovery, behavior cloning. |