{"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/critic-guided-segmentation-of-rewarding","title":"Critic Guided Segmentation of Rewarding Objects in First-Person Views","arxiv_id":"2107.09540","date":"2021-07-20","proceeding":null,"authors":["Andrew Melnik","Augustin Harter","Christian Limberg","Krishan Rana","Niko Suenderhauf","Helge Ritter"],"abstract":"This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition. Video demonstration and code: https://rebrand.ly/critic-guided-segmentation","url_abs":"https://arxiv.org/abs/2107.09540v1","url_pdf":"https://arxiv.org/pdf/2107.09540v1.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":"critic-guided-segmentation-of-rewarding","repo_url":"https://github.com/ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2107.09540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09540"}},"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/ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"36bc4b160f30295d","entry":"get_moving_avg","repo":"ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views","repo_kind":"listed","path":"TrainHandler.py","file_url":"https://github.com/ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views/blob/HEAD/TrainHandler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36bc4b160f30295d"}},{"code_sha256_prefix":"660cafa8836fab2a","entry":"get_vgg_features","repo":"ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views","repo_kind":"listed","path":"nets.py","file_url":"https://github.com/ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views/blob/HEAD/nets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"660cafa8836fab2a"}},{"code_sha256_prefix":"175f916ec1005f7b","entry":"make_plotbar","repo":"ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views","repo_kind":"listed","path":"TrainHandler.py","file_url":"https://github.com/ndrwmlnk/critic-guided-segmentation-of-rewarding-objects-in-first-person-views/blob/HEAD/TrainHandler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"175f916ec1005f7b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}