[
    {
        "id": "osp-16508",
        "type": "article-journal",
        "title": "مُحكِّم سياسة نموذج العالم لتعلم التعزيز الموجّه بالهدف",
        "author": [
            {
                "family": "Quan",
                "given": "Junwei"
            },
            {
                "family": "Opryshko",
                "given": "Evgenii"
            },
            {
                "family": "Rhinehart",
                "given": "Nicholas"
            },
            {
                "family": "Gilitschenski",
                "given": "Igor"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/world-model-policy-arbiter-for-goal-conditioned-reinforcement-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        }
    }
]