{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/value-prediction-network","title":"Value Prediction Network","arxiv_id":"1707.03497","date":"2017-07-11","proceeding":"NeurIPS 2017 12","authors":["Junhyuk Oh","Satinder Singh","Honglak Lee"],"abstract":"This paper proposes a novel deep reinforcement learning (RL) architecture,\ncalled Value Prediction Network (VPN), which integrates model-free and\nmodel-based RL methods into a single neural network. In contrast to typical\nmodel-based RL methods, VPN learns a dynamics model whose abstract states are\ntrained to make option-conditional predictions of future values (discounted sum\nof rewards) rather than of future observations. Our experimental results show\nthat VPN has several advantages over both model-free and model-based baselines\nin a stochastic environment where careful planning is required but building an\naccurate observation-prediction model is difficult. Furthermore, VPN\noutperforms Deep Q-Network (DQN) on several Atari games even with\nshort-lookahead planning, demonstrating its potential as a new way of learning\na good state representation.","url_abs":"http://arxiv.org/abs/1707.03497v2","url_pdf":"http://arxiv.org/pdf/1707.03497v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"value-prediction-network","repo_url":"https://github.com/junhyukoh/value-prediction-network","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"value-prediction-network","repo_url":"https://github.com/geohot/twitchcoq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"value-prediction","task_name":"Value prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-2600-alien","task":"Atari Games","dataset":"Atari 2600 Alien","model":"VPN","rank_in_archive_order":34,"of":49,"metrics":{"Score":"1429"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-amidar","task":"Atari Games","dataset":"Atari 2600 Amidar","model":"VPN","rank_in_archive_order":30,"of":48,"metrics":{"Score":"641"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-crazy-climber","task":"Atari Games","dataset":"Atari 2600 Crazy Climber","model":"VPN","rank_in_archive_order":42,"of":49,"metrics":{"Score":"54119"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-enduro","task":"Atari Games","dataset":"Atari 2600 Enduro","model":"VPN","rank_in_archive_order":36,"of":48,"metrics":{"Score":"382"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-frostbite","task":"Atari Games","dataset":"Atari 2600 Frostbite","model":"VPN","rank_in_archive_order":22,"of":53,"metrics":{"Score":"3811"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-krull","task":"Atari Games","dataset":"Atari 2600 Krull","model":"VPN","rank_in_archive_order":9,"of":45,"metrics":{"Score":"15930"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-ms-pacman","task":"Atari Games","dataset":"Atari 2600 Ms. Pacman","model":"VPN","rank_in_archive_order":30,"of":47,"metrics":{"Score":"2689"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-qbert","task":"Atari Games","dataset":"Atari 2600 Q*Bert","model":"VPN","rank_in_archive_order":29,"of":57,"metrics":{"Score":"14517"},"uses_additional_data":false},{"leaderboard":"/sota/atari-games-on-atari-2600-seaquest","task":"Atari Games","dataset":"Atari 2600 Seaquest","model":"VPN","rank_in_archive_order":31,"of":57,"metrics":{"Score":"5628"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.03497","atlas_url":"https://app.syntology.ai/?focus=1707.03497","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1707.03497"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.03497\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.03497"},"call":"get_concepts_for_paper(arxiv_id=\"1707.03497\")"}],"by_repo":[{"repo":"junhyukoh/value-prediction-network","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"geohot/twitchcoq","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cbdee7e1b18d605ad5de896df9c20711fedcf1dfa646429af37531c8040cfaa1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}