Article Instance

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

{
    "pk": 27023,
    "title": "Learning to reinforcement learn",
    "subtitle": null,
    "abstract": "In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number ofchallenging task domains, but are constrained by a demand for large training sets. A critical present objective is thus to developdeep RL methods that can adapt rapidly to new tasks. In the present work we introduce a novel approach to this challenge,which we refer to as deep meta-reinforcement learning. Previous work has shown that recurrent networks can support meta-learning in a fully supervised context. We extend this approach to the RL setting. What emerges is a system that is trainedusing one RL algorithm, but whose recurrent dynamics implement a second, quite separate RL procedure. This second, learnedRL algorithm can differ from the original one in arbitrary ways and exploit structure in the training domain. We unpack thesepoints in five proof-of-concept experiments to examine key aspects of deep meta-RL.",
    "language": "eng",
    "license": {
        "name": "",
        "short_name": "",
        "text": null,
        "url": ""
    },
    "keywords": [],
    "section": "Talks: Papers",
    "is_remote": true,
    "remote_url": "https://escholarship.org/uc/item/1tn6q2t7",
    "frozenauthors": [
        {
            "first_name": "Jane",
            "middle_name": "",
            "last_name": "Wang",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Zeb",
            "middle_name": "",
            "last_name": "Kurth-Nelson",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Hubert",
            "middle_name": "",
            "last_name": "Soyer",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Joel",
            "middle_name": "",
            "last_name": "Leibo",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Dhruva",
            "middle_name": "",
            "last_name": "Tirumala",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Remi",
            "middle_name": "",
            "last_name": "Munos",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Charles",
            "middle_name": "",
            "last_name": "Blundell",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Dharshan",
            "middle_name": "",
            "last_name": "Kumaran",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        },
        {
            "first_name": "Matt",
            "middle_name": "",
            "last_name": "Botvinick",
            "name_suffix": "",
            "institution": "DeepMind",
            "department": ""
        }
    ],
    "date_submitted": null,
    "date_accepted": null,
    "date_published": "2017-01-01T18:00:00Z",
    "render_galley": null,
    "galleys": [
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/27023/galley/16659/download/"
        }
    ]
}