abstracts |
[]
|
container |
{'state': 'active', 'ident': 'ee7h5mwavff7fgllkvmbhhz5le', 'revision': 'dd672890-3bc5-4990-aebd-06aea7ef3480', 'redirect': None, 'extra': {'acronym': 'NeurIPS', 'dblp': {'prefix': 'conf/nips'}, 'urls': ['http://neurips.cc/']}, 'edit_extra': None, 'name': 'Neural Information Processing Systems', 'container_type': 'conference-series', 'publication_status': None, 'publisher': None, 'issnl': None, 'issne': None, 'issnp': None, 'wikidata_qid': 'Q1961016'}
|
container_id |
ee7h5mwavff7fgllkvmbhhz5le
|
contribs[] |
{'index': 0, 'creator_id': None, 'creator': None, 'raw_name': 'Tommi S. Jaakkola', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
{'index': 1, 'creator_id': None, 'creator': None, 'raw_name': 'Satinder P. Singh', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
{'index': 2, 'creator_id': None, 'creator': None, 'raw_name': 'Michael I. Jordan', 'given_name': None, 'surname': None, 'role': 'author', 'raw_affiliation': None, 'extra': None}
|
ext_ids |
{'doi': None, 'wikidata_qid': None, 'isbn13': None, 'pmid': None, 'pmcid': None, 'core': None, 'arxiv': None, 'jstor': None, 'ark': None, 'mag': None, 'doaj': None, 'dblp': 'conf/nips/JaakkolaSJ94', 'oai': None, 'hdl': None}
|
files[] |
{'state': 'active', 'ident': 'pboio736dbhv5ov6ov6r546ppm', 'revision': '10283af0-10f8-4669-8d34-cbfb6fbf1324', 'redirect': None, 'extra': None, 'edit_extra': None, 'size': 1584184, 'md5': '9d0075d43521348f0b658a8cc4dc30a1', 'sha1': 'fd4fd21018c899f6125a15ed161244880221cf3f', 'sha256': '3039e7365408530906e3a5e96c823dd68d04855bb64a4471e45bca10039f6fcb', 'urls': [{'url': 'http://papers.nips.cc/paper/951-reinforcement-learning-algorithm-for-partially-observable-markov-decision-problems.pdf', 'rel': 'web'}, {'url': 'https://web.archive.org/web/20160411081901/http://papers.nips.cc/paper/951-reinforcement-learning-algorithm-for-partially-observable-markov-decision-problems.pdf', 'rel': 'webarchive'}], 'mimetype': 'application/pdf', 'content_scope': None, 'release_ids': ['nvsm7pcrdfcuxevwx76uka2fjq'], 'releases': None}
|
filesets |
[]
|
issue |
|
language |
|
license_slug |
|
number |
|
original_title |
|
pages |
345-352
|
publisher |
|
refs |
[]
|
release_date |
|
release_stage |
published
|
release_type |
paper-conference
|
release_year |
1994
|
subtitle |
|
title |
Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems
|
version |
|
volume |
|
webcaptures |
[]
|
withdrawn_date |
|
withdrawn_status |
|
withdrawn_year |
|
work_id |
jiueyp7uenhkdol3ysliawzx4e
|