Article Instance

HTTP 200 OK
Allow: GET
Content-Type: application/json
Vary: Accept

{
    "pk": 23983,
    "title": "Can reinforcement learning model learning across development? Online lifelong learning through adaptive intrinsic motivation",
    "subtitle": null,
    "abstract": "Reinforcement learning is a powerful model of animal learning in brief, controlled experimental conditions, but does not readily explain the development of behavior over an animal's whole lifetime.  In this paper, we describe a framework to address this shortcoming by introducing the single-life reinforcement learning setting to cognitive science. We construct an agent with two learning systems: an extrinsic learner that learns within a single lifetime, and an intrinsic learner that learns across lifetimes, equipping the agent with intrinsic motivation. We show that this model outperforms heuristic benchmarks and recapitulates a transition from exploratory to habit-driven behavior, while allowing the agent to learn an interpretable value function. We formulate a precise definition of intrinsic motivation and discuss the philosophical implications of using reinforcement learning as a model of behavior in the real world.",
    "language": "eng",
    "license": {
        "name": "",
        "short_name": "",
        "text": null,
        "url": ""
    },
    "keywords": [
        {
            "word": "Cognitive Neuroscience; Philosophy; Learning; Machine learning; Neural Networks"
        }
    ],
    "section": "Papers with Poster Presentation",
    "is_remote": true,
    "remote_url": "https://escholarship.org/uc/item/1td977rv",
    "frozenauthors": [
        {
            "first_name": "Kai",
            "middle_name": "J",
            "last_name": "Sandbrink",
            "name_suffix": "",
            "institution": "University of Oxford",
            "department": ""
        },
        {
            "first_name": "Brian",
            "middle_name": "",
            "last_name": "Christian",
            "name_suffix": "",
            "institution": "University of Oxford",
            "department": ""
        },
        {
            "first_name": "Linas",
            "middle_name": "M.",
            "last_name": "Nasvytis",
            "name_suffix": "",
            "institution": "Harvard University",
            "department": ""
        },
        {
            "first_name": "Christian",
            "middle_name": "",
            "last_name": "Schroeder de Witt",
            "name_suffix": "",
            "institution": "University of Oxford",
            "department": ""
        },
        {
            "first_name": "Patrick",
            "middle_name": "",
            "last_name": "Butlin",
            "name_suffix": "",
            "institution": "University of Oxford",
            "department": ""
        }
    ],
    "date_submitted": null,
    "date_accepted": null,
    "date_published": "2024-01-01T18:00:00Z",
    "render_galley": null,
    "galleys": [
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/23983/galley/13577/download/"
        },
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/23983/galley/20976/download/"
        }
    ]
}