{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/vip-towards-universal-visual-reward-and","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","arxiv_id":"2210.00030","date":"2022-09-30","proceeding":null,"authors":["Yecheng Jason Ma","Shagun Sodhani","Dinesh Jayaraman","Osbert Bastani","Vikash Kumar","Amy Zhang"],"abstract":"Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question. We introduce $\\textbf{V}$alue-$\\textbf{I}$mplicit $\\textbf{P}$re-training (VIP), a self-supervised pre-trained visual representation capable of generating dense and smooth reward functions for unseen robotic tasks. VIP casts representation learning from human videos as an offline goal-conditioned reinforcement learning problem and derives a self-supervised dual goal-conditioned value-function objective that does not depend on actions, enabling pre-training on unlabeled human videos. Theoretically, VIP can be understood as a novel implicit time contrastive objective that generates a temporally smooth embedding, enabling the value function to be implicitly defined via the embedding distance, which can then be used to construct the reward for any goal-image specified downstream task. Trained on large-scale Ego4D human videos and without any fine-tuning on in-domain, task-specific data, VIP's frozen representation can provide dense visual reward for an extensive set of simulated and $\\textbf{real-robot}$ tasks, enabling diverse reward-based visual control methods and significantly outperforming all prior pre-trained representations. Notably, VIP can enable simple, $\\textbf{few-shot}$ offline RL on a suite of real-world robot tasks with as few as 20 trajectories.","url_abs":"https://arxiv.org/abs/2210.00030v2","url_pdf":"https://arxiv.org/pdf/2210.00030v2.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":"vip-towards-universal-visual-reward-and","repo_url":"https://github.com/facebookresearch/vip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2210.00030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00030"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/vip","reach":null}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"f77bfd3f1417e10b","entry":"VIP","repo":"facebookresearch/vip","repo_kind":"official","path":"vip/models/model_vip.py","file_url":"https://github.com/facebookresearch/vip/blob/HEAD/vip/models/model_vip.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f77bfd3f1417e10b"}},{"code_sha256_prefix":"f8a214d48c5442e3","entry":"make_network","repo":"facebookresearch/vip","repo_kind":"official","path":"vip/train_vip.py","file_url":"https://github.com/facebookresearch/vip/blob/HEAD/vip/train_vip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f8a214d48c5442e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}