Article Instance

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

{
    "pk": 31367,
    "title": "A Connectionist Architecture for Sequential Decision Learning",
    "subtitle": null,
    "abstract": "a connectionist architecture and learning algorithm for sequential decision learning are presented. The architecture provides representations for probabilities and utilities. The learning algorithm provides a mechanism to learn from longterm rewards/utilities while observing information available locally in time. The mechanism is based on gradient ascent on the current estimate of the long-term reward in the weight spju^e defined by a \"policy\" network. The learning principle can be seen as a generalization of previous methods proposed to implement \"policy iteration\" mechanisms with connectionist networks. The algorithm is simulated for an \"agent\" moving in an environment described as a simple one-dimensional random walk. Results show the agent discovers optimal moving strategies in simple caises and learns how to avoid short-term suboptimal rewards in order to maximize long-term rewards in more complex cases.",
    "language": "eng",
    "license": {
        "name": "",
        "short_name": "",
        "text": null,
        "url": ""
    },
    "keywords": [],
    "section": "Posters",
    "is_remote": true,
    "remote_url": "https://escholarship.org/uc/item/16237234",
    "frozenauthors": [
        {
            "first_name": "Yves",
            "middle_name": "",
            "last_name": "Chauvin",
            "name_suffix": "",
            "institution": "Stanford University",
            "department": ""
        }
    ],
    "date_submitted": null,
    "date_accepted": null,
    "date_published": "1992-01-01T18:00:00Z",
    "render_galley": null,
    "galleys": [
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/31367/galley/22436/download/"
        }
    ]
}